Skip to main content
Glama

narrate_change

Read-only

Return a grounded reading of what changed between passes.

Sibling of :func:`describe_scene`. The composite and the per-block dB grid
are produced deterministically; a model only narrates change those numbers
support. Pass the STAC URLs in time order; mixed polarizations are refused.

This tool **streams Umbra COGs** to build the composite, so a public
community host refuses it (use a local ``uvx --from 'umbra-py[mcp]'
umbra-mcp`` server, or describe each pass with :func:`describe_scene` /
:func:`quicklook` on baked previews). On a local server:

- **No vision key:** returns the composite as an MCP image block plus a
  reading kit (SAR change primer, the dB grid, the JSON schema). **You**
  (the client's model) narrate, grounded in the numbers.
- **Key configured:** sends picture + grid to that vision model, validates
  through ``parse_narration``, and returns a provenance-stamped
  ``{summary, changes[], confidence, caveats[], change_stats}`` object.

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": {
      "urls": "<urls>"
    },
    "name": "narrate_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
dbNoDecibel stretch for the change picture. Default false.
urlsYesSTAC JSON URLs or item ids of at least two passes, in time order. Mixed polarizations are refused. The public host refuses this tool.
assetNoProduct to composite and measure. Default GEC.GEC
modelNoVision model id when this server holds an API key. Omit for the default. Unused on the no-key kit path.
max_sizeNoOverview size cap in pixels for the composite. Default 1024.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / asset / description
      Added value: +"Product to composite and measure. Default GEC."
    • addedInput schema / properties / db / description
      Added value: +"Decibel stretch for the change picture. Default false."
    • addedInput schema / properties / max_size / description
      Added value: +"Overview size cap in pixels for the composite. Default 1024."
    • 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 / urls / description
      Added value: +"STAC JSON URLs or item ids of at least two passes, in time order. Mixed polarizations are refused. The public host refuses this tool."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

readOnlyHint=true is consistent with the described behaviour, and the description adds substantial context beyond it: the tool streams Umbra COGs, the public host refuses it, and the output differs radically by configuration — a composite image block plus reading kit with no vision key, versus a provenance-stamped {summary, changes[], confidence, caveats[], change_stats} object validated through parse_narration when a key exists.

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?

Well front-loaded — the one-line purpose, the sibling relationship, and the hard constraints come before the environment and output-mode detail, which is broken into scannable bullets. It is dense and slightly long, but almost every clause carries operational information an agent needs.

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 that streams remote COGs, has two very different return paths, and no output schema, the description covers environment restrictions, input ordering, refusal conditions, and the shape of each response mode. Nothing an agent needs to call it correctly or interpret its result is missing.

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 description coverage is 100%, so the schema already documents urls, db, asset, model, and max_size. The description reinforces the ordering and polarization constraints on urls but adds little field-level meaning beyond what the schema states, which is the expected baseline when the schema does the heavy lifting.

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?

The first line names a specific verb and resource: 'Return a grounded reading of *what changed* between passes.' It immediately distinguishes itself from its sibling by declaring 'Sibling of :func:`describe_scene`' and explains the division of labour (deterministic composite and dB grid, model only narrates what the numbers support).

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?

Explicit routing: on a public community host this tool is refused, and the description names concrete alternatives (run a local uvx server, or use describe_scene / quicklook on baked previews). It also states the input precondition (URLs in time order) and the exclusion (mixed polarizations refused).

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.