# Did It Work? (org.diditwork/did-it-work): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/org.diditwork%2Fdid-it-work/versions/latest)
- Connected to: https://api.diditwork.org/mcp
- Homepage: https://diditwork.org/agents/mcp
- Scoring rules: v2
- Tools: 22
- Average: 64.0 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how Did It Work? (org.diditwork/did-it-work)'s tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

## Across the server

No server-wide issues.

## Tools

- `get_trust`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: org_id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: org_id. Name the tool or the place that returns it, or models look it up first.
- `list_ledger_records`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: org_id, evaluator, status, intervention_id, record_kind.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `get_ledger_record`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `verdict_chain`: 51 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: org_id.
  - Minor: Required identifiers whose description does not say where the value comes from: org_id. Name the tool or the place that returns it, or models look it up first.
- `get_org`: 52 / 100
  - Major: Arguments without a description: id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `get_values_profile`: 52 / 100
  - Major: Arguments without a description: id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `get_meta`: 54 / 100
  - Minor: Says nothing about what it returns.
- `allocate_portfolio`: 58 / 100
  - Major: Arguments without a description: budget_usd, top_n, risk, geography, tax, include_funds.
  - Minor: String arguments with no constraint or example: geography, tax.
  - Minor: The meaning of the boolean argument include_funds is unclear.
- `get_tax`: 59 / 100
  - Major: Arguments without a description: org_id.
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: org_id. Name the tool or the place that returns it, or models look it up first.
- `compare_charities`: 64 / 100
  - Minor: Says nothing about what it returns.
  - Minor: Required identifiers whose description does not say where the value comes from: ids. Name the tool or the place that returns it, or models look it up first.
- `create_giving_intent`: 64 / 100
  - Major: Arguments without a description: org_id, amount_usd, vehicle, values_profile_id.
  - Minor: The description mentions none of its 3 or more arguments.
  - Minor: Required identifiers whose description does not say where the value comes from: org_id. Name the tool or the place that returns it, or models look it up first.
- `report_decision_effect`: 64 / 100
  - Minor: Says nothing about what it returns.
- `list_leaderboards`: 65 / 100
  - Minor: No `required` list, so every argument is optional.
- `list_values_profiles`: 65 / 100
  - Minor: Says nothing about what it returns.
- `estimate_impact`: 66 / 100
  - Major: Arguments without a description: org_id, gift_usd.
  - Minor: Required identifiers whose description does not say where the value comes from: org_id. Name the tool or the place that returns it, or models look it up first.
- `recommend_charity`: 72 / 100
  - Major: Arguments without a description: budget_usd, risk, geography, require_geography, tax, limit.
  - Minor: The meaning of the boolean argument require_geography is unclear.
- `get_review_queue`: 76 / 100
  - Minor: No `required` list, so every argument is optional.
- `decision_brief`: 77 / 100
  - Minor: The description is long (944 words). It helps selection but costs steps and tokens.
  - Minor: Arguments without a description: cause.
  - Minor: No `required` list, so every argument is optional.
- `search_orgs`: 78 / 100
  - Minor: The description is long (1276 words). It helps selection but costs steps and tokens.
  - Minor: Arguments without a description: cause, intent.
  - Minor: No `required` list, so every argument is optional.
- `list_charities`: 81 / 100
  - Minor: No `required` list, so every argument is optional.
- `get_claim`: 89 / 100
  - Minor: Required identifiers whose description does not say where the value comes from: id. Name the tool or the place that returns it, or models look it up first.
- `list_claims`: 89 / 100
  - Minor: No `required` list, so every argument is optional.

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

[All scored servers](https://forecall.dev/en/servers)