Skip to main content
Glama

find_similar

Read-only

Find archived scenes that look like the acquisition at url.

This is the one search that lives in the pixels, not the metadata: where
``search_catalog`` filters by date/bbox/task-name, this renders the query
item's quicklook, embeds it, and ranks the pre-embedded scene index by visual
(cosine) similarity — "find scenes that look like this flooded field / crowded
berth / runway". The query item is excluded from its own results.

Requires a scene-embedding index built ahead of time with ``umbra embed
build`` (a sidecar ``catalog.embed.db`` beside the catalog index) and a
user-supplied multimodal embedding key (``OPENAI_API_KEY``, optionally
``OPENAI_BASE_URL`` / ``UMBRA_SCENE_EMBED_MODEL``) — the only model call is
turning the query image into a vector; ranking is deterministic. ``asset``
picks which product's quicklook to embed (default ``GEC``; match how the index
was built); ``model`` must match the index's embedding model. Returns the
ranked matches as compact records (each with the acquisition's ``href``, so
hand it to ``get_item`` / ``quicklook`` / ``change_composite`` next) plus the
attribution line.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "find_similar"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesSTAC JSON URL or index item id of the scene to match. The public host also accepts a filename or stem in the index.
assetNoProduct whose quicklook is embedded. Default GEC. Match how the scene index was built.GEC
modelNoEmbedding model id. Must match the scene index. Omit for the server default.
top_kNoMaximum matches to return. Default 10.
min_scoreNoMinimum cosine similarity. Default 0. Matches below it are dropped.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / asset / description
      Added value: +"Product whose quicklook is embedded. Default GEC. Match how the scene index was built."
    • addedInput schema / properties / min_score / description
      Added value: +"Minimum cosine similarity. Default 0. Matches below it are dropped."
    • addedInput schema / properties / model / description
      Added value: +"Embedding model id. Must match the scene index. Omit for the server default."
    • addedInput schema / properties / top_k / description
      Added value: +"Maximum matches to return. Default 10."
    • addedInput schema / properties / url / description
      Added value: +"STAC JSON URL or index item id of the scene to match. The public host also accepts a filename or stem in the index."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses that this requires a prebuilt `catalog.embed.db` sidecar and a user-supplied embedding key (OPENAI_API_KEY, optional base URL/model env var), that only the query image is sent to a model while ranking is deterministic, and that the query item is excluded from its own results. These are exactly the operational facts an agent cannot infer from the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The key differentiator is front-loaded in the first two sentences, and the remaining sentences cover prerequisites and returns. It is dense and parenthetical-heavy, but nearly every clause carries operational information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with an output schema, it covers what the schema cannot: index prerequisites, credential needs, the exclusion of the query item, and a summary of the returned records (compact matches with `href` plus attribution). An agent has everything needed to decide to call it and to configure the environment correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description reinforces the coupling constraints for `asset` and `model` (both must match how the index was built), but that constraint is already stated in the schema descriptions, and `top_k` / `min_score` are not discussed at all — so it adds little meaning beyond structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find archived scenes that look like the acquisition at url') and immediately names the mechanism — pixel-level visual similarity rather than metadata. It explicitly contrasts with the sibling `search_catalog` ('where search_catalog filters by date/bbox/task-name'), so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use condition with concrete examples ('find scenes that look like this flooded field / crowded berth / runway') and an explicit when-not-to-use by naming the metadata-search alternative. It also states the prerequisite index build and the follow-up tools (`get_item`, `quicklook`, `change_composite`) to call next.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.