# Umbra open SAR archive (io.github.reesehammer/umbra-mcp): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.reesehammer%2Fumbra-mcp/versions/latest)
- Connected to: https://api.umbra-py.space/mcp
- Repository: https://github.com/reesehammer/umbra-py
- Scoring rules: v2
- Tools: 19
- Average: 60.7 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how Umbra open SAR archive (io.github.reesehammer/umbra-mcp)'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

- `timescan`: 42 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: urls, asset, db, max_size.
  - Minor: The meaning of the boolean argument db is unclear.
- `describe_scene`: 45 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: url, asset, db, max_size, model, preview.
  - Minor: String arguments with no constraint or example: url.
  - Minor: The meaning of the boolean argument db is unclear.
- `narrate_change`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: urls, asset, db, max_size, model.
  - Minor: The meaning of the boolean argument db is unclear.
- `stamp_narration`: 48 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: reading, item_ids, asset, model, change_stats.
- `change_composite`: 49 / 100
  - Major: Arguments without a description: urls, asset, db, max_size.
  - Minor: The meaning of the boolean argument db is unclear.
- `geocode_place`: 50 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: query.
  - Minor: String arguments with no constraint or example: query.
- `watch_site`: 53 / 100
  - Major: Arguments without a description: place, area, bbox, fuzzy, start, end, products, name, reset, local.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The meaning of the boolean argument fuzzy is unclear.
  - Minor: The meaning of the boolean argument reset is unclear.
  - Major: It may be destructive, but destructiveHint is not set.
- `download_asset`: 56 / 100
  - Minor: The description is long (451 words). It helps selection but costs steps and tokens.
  - Major: Arguments without a description: url, asset, dest_dir, confirm.
  - Minor: String arguments with no constraint or example: url.
  - Minor: The meaning of the boolean argument confirm is unclear.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `find_similar_text`: 60 / 100
  - Major: Arguments without a description: query, top_k, min_score, model.
  - Minor: String arguments with no constraint or example: query.
- `quicklook`: 60 / 100
  - Major: Arguments without a description: url, asset, db, max_size, preview.
  - Minor: String arguments with no constraint or example: url.
  - Minor: The meaning of the boolean argument db is unclear.
- `find_similar`: 62 / 100
  - Major: Arguments without a description: url, asset, top_k, min_score, model.
  - Minor: String arguments with no constraint or example: url.
- `index_stats`: 65 / 100
  - Major: Says nothing about when to use it, or when not to.
- `stamp_description`: 65 / 100
  - Major: Arguments without a description: reading, item_id, asset, model, image.
- `get_item`: 73 / 100
  - Major: Arguments without a description: url.
  - Minor: String arguments with no constraint or example: url.
  - Major: The name is made of generic words only.
- `find_repeat_sites`: 75 / 100
  - Minor: The description is long (1568 words). It helps selection but costs steps and tokens.
  - Major: Arguments without a description: bbox, intersects, place, area, fuzzy, start, end, products, polarizations, min_incidence, max_incidence, max_resolution, limit, top, min_passes, rank_by, active_since, active_before, first_since, first_before, max_revisit_days, median_revisit_days, min_span_days, max_span_days, local.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The meaning of the boolean argument fuzzy is unclear.
- `pick_change_interval`: 75 / 100
  - Major: Arguments without a description: urls, asset, max_size, change_threshold_db, extent, crs.
- `search_catalog`: 75 / 100
  - Minor: The description is long (518 words). It helps selection but costs steps and tokens.
  - Major: Arguments without a description: bbox, intersects, place, area, fuzzy, semantic, min_score, start, end, products, polarizations, min_incidence, max_incidence, max_resolution, canonical, limit, max_per_task, local.
  - Minor: No `required` list, so every argument is optional.
  - Minor: The meaning of the boolean argument fuzzy is unclear.
  - Minor: The meaning of the boolean argument semantic is unclear.
- `stack_stats`: 75 / 100
  - Minor: The description is long (603 words). It helps selection but costs steps and tokens.
  - Major: Arguments without a description: urls, asset, bbox, max_size, extent, crs, change_threshold_db, blocks, block_series, speckle_filter, speckle_window.
  - Minor: The meaning of the boolean argument block_series is unclear.
- `stack_provenance`: 78 / 100
  - Major: Arguments without a description: urls, asset.

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)