Skip to main content
Glama

describe_scene

Read-only

Return a SAR-literate reading of the scene at url.

The picture and the metadata card are produced deterministically; a model
only interprets them. How that model is reached depends on whether this
process holds a vision key:

- **No key** (the public community host): this tool does **not** call a
  vision model. It returns the PNG plus a reading kit (SAR rules, the
  metadata card, the JSON schema). Produce the JSON, then call
  :func:`stamp_description` — that is the validation boundary
  (provenance-stamped ``{summary, observed_features, confidence,
  caveats}``). Until you stamp it, your prose is not pipeline output.
  A baked preview is typically 512 px; the kit names the size and
  that a local server can stream a higher-resolution GeoTIFF.
- **Key configured** (local stdio): sends the picture to that vision
  model, validates through ``parse_description``, and returns the
  stamped object directly.

The packaged SAR rules are the value over just looking at ``quicklook``:
brightness is backscatter not sunlight, speckle is not structure, a dark
patch may be radar shadow not water, one frame is not change.

``preview`` defaults to ``"auto"``: a baked catalog preview if this server
has one, else a fresh render. ``"render"`` is refused on the public host.

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": "describe_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
dbNoDecibel stretch for a fresh render. Default true. A baked preview is always decibel.
urlYesSTAC JSON URL or index item id. The public host also accepts a product filename or acquisition stem that is in the index.
assetNoProduct to picture. Default GEC.GEC
modelNoVision model id when this server holds an API key. Omit for the default. Unused on the no-key kit path.
previewNoauto (default) uses a baked preview when present, else renders. baked refuses if none. render always streams a COG and is refused on the public host.auto
max_sizeNoLongest side in pixels for a fresh render. Default 1024. A baked preview may be smaller; the kit says when this was ignored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / asset / description
      Added value: +"Product to picture. Default GEC."
    • addedInput schema / properties / db / description
      Added value: +"Decibel stretch for a fresh render. Default true. A baked preview is always decibel."
    • addedInput schema / properties / max_size / description
      Added value: +"Longest side in pixels for a fresh render. Default 1024. A baked preview may be smaller; the kit says when this was ignored."
    • addedInput schema / properties / model / description
      Added value: +"Vision model id when this server holds an API key. Omit for the default. Unused on the no-key kit path."
    • addedInput schema / properties / preview / description
      Added value: +"auto (default) uses a baked preview when present, else renders. baked refuses if none. render always streams a COG and is refused on the public host."
    • addedInput schema / properties / url / description
      Added value: +"STAC JSON URL or index item id. The public host also accepts a product filename or acquisition stem that is in the index."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: it discloses deterministic image/card production, that no vision model is called on the public host, that prose is not pipeline output until stamped, that baked previews are typically 512 px and may ignore max_size, and that one frame is not change. These are the operational and interpretation caveats an agent needs and cannot get from the schema.

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?

Purpose is front-loaded and the branching key/no-key structure maps to real decision points rather than padding. Minor deductions for RST markup noise (``:func:``) and some repetition between the bullet on preview and the closing paragraph.

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 6-parameter tool with no output schema, the description covers return shape, both execution paths, the required follow-up validation call, and interpretation caveats about SAR imagery. Nothing an agent needs to invoke it correctly or interpret its output is missing.

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

Parameters4/5

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 earns above that by explaining the consequence of ``preview="auto"`` (baked if present, else fresh render) and by noting the kit reports when a baked preview ignored the requested size. It mostly restates schema-documented behavior otherwise, so it does not reach a 5.

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?

Opens with a specific verb and resource ("Return a SAR-literate reading of the scene at ``url``") and immediately differentiates itself from the ``quicklook`` sibling by naming the packaged SAR rules as the value-add. The body then clarifies the two possible return shapes (PNG + reading kit vs. stamped object), so an agent knows exactly what it gets without opening the 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?

Explicitly branches on runtime capability: with no vision key it returns a kit and the agent must call ``stamp_description`` as the validation boundary; with a key it returns the stamped object directly. It also states that ``preview="render"`` is refused on the public host, which is a concrete when-not condition an agent can act on.

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.