Skip to main content
Glama

watch_site

Destructive

Report only the acquisitions new since the last check of this site.

SAR's value for monitoring is its cadence, so the natural workflow is
*standing*: run the same search each time and act only on what changed. This
tool packages that idempotent delta — call it in one turn, come back a day
(or a session) later and call it again, and it returns just the passes
published in between, not the whole list again. The scheduler is you: ask the
agent to check the site, and it reports the delta.

Define the site with the same filters as ``search_catalog`` — ``place``
(geocoded to a bbox), ``area`` (task/site-name substring, loosened by
``fuzzy``), ``bbox``, ``products``, and ``start``/``end`` date bounds. The
watch is identified by a stable ``name`` derived from those filters (pass an
explicit ``name`` to run several independent watches over the same site);
``reset=True`` re-establishes the baseline, reporting everything as new.

State persists in the local catalog index's ``meta`` table (created on first
use), so a watch survives across sessions with no extra setup. ``local``
selects the search backend exactly as in ``search_catalog`` — leave it unset
to use the on-disk index when present and a live S3 walk otherwise; for true
monitoring a live walk (``local=false``) catches freshly published passes.
**No model is called** — this is pure set arithmetic over the deterministic
search — and the returned ``new_items`` are context cards ready to hand
straight to ``change_composite`` / ``timescan``, closing the standing-analyst
loop (new pass → composite → describe) without leaving the conversation.

On the public host (``umbra serve --public``, COG streaming off) nothing
is stored. Every call reports the current matches as new, says so in
``note``, and caps ``new_items`` at 50 (``new_total`` is the full count).
The watch name is capped at 128 characters. A local server still persists
the baseline in the index.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "watch_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoInclusive acquisition-date upper bound. Same grammar as search_catalog end.
areaNoTask-name substring. With fuzzy, a loose token match.
bboxNoWGS84 [min_lon, min_lat, max_lon, max_lat]. When set, place is not geocoded.
nameNoStable watch id. Omit to derive one from the filters. The public host keeps at most 128 characters.
fuzzyNoLoose task-name match for area. No model call.
localNoTrue uses only the local index; False forces a live walk. Omit to use the index when present. True cannot be combined with a Canopy token.
placeNoFree-text place. Geocoded to a bbox only when bbox is omitted.
resetNoTrue discards the stored baseline and reports every current match as new. Default false.
startNoInclusive acquisition-date lower bound. Same grammar as search_catalog start.
productsNoKeep items that expose one of these types (GEC, CSI, SIDD, SICD, CPHD).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / area / description
      Added value: +"Task-name substring. With fuzzy, a loose token match."
    • addedInput schema / properties / bbox / description
      Added value: +"WGS84 [min_lon, min_lat, max_lon, max_lat]. When set, place is not geocoded."
    • addedInput schema / properties / end / description
      Added value: +"Inclusive acquisition-date upper bound. Same grammar as search_catalog end."
    • addedInput schema / properties / fuzzy / description
      Added value: +"Loose task-name match for area. No model call."
    • addedInput schema / properties / local / description
      Added value: +"True uses only the local index; False forces a live walk. Omit to use the index when present. True cannot be combined with a Canopy token."
    • addedInput schema / properties / name / description
      Added value: +"Stable watch id. Omit to derive one from the filters. The public host keeps at most 128 characters."
    • addedInput schema / properties / place / description
      Added value: +"Free-text place. Geocoded to a bbox only when bbox is omitted."
    • addedInput schema / properties / products / description
      Added value: +"Keep items that expose one of these types (GEC, CSI, SIDD, SICD, CPHD)."
    • addedInput schema / properties / reset / description
      Added value: +"True discards the stored baseline and reports every current match as new. Default false."
    • addedInput schema / properties / start / description
      Added value: +"Inclusive acquisition-date lower bound. Same grammar as search_catalog start."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it discloses that state persists in the local catalog index's meta table (created on first use), that no model is called, that the public host stores nothing and caps new_items at 50 with the true count in new_total, and that watch names are capped at 128 characters. This is consistent with readOnlyHint=false / destructiveHint=true: the tool writes a baseline, and reset discards it.

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

Conciseness3/5

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

The delta behavior and the public-host caveat are front-loaded, but the middle is padded with framing prose ('SAR's value for monitoring is its cadence', 'closing the standing-analyst loop') that an agent does not need. The technical content is dense and useful, yet a third of the length could be cut without losing a decision-relevant fact.

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 10-parameter, all-optional tool with an output schema and annotations, the description covers everything an agent needs: persistence semantics, reset behavior, backend selection, public-host degradation, and the hand-off to downstream tools. Return value shape is left to the output schema, which is appropriate.

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 already 100%, so the baseline would be 3; the description goes further by explaining that place is geocoded to a bbox (and not when bbox is set), that area is loosened by fuzzy, that name is derived from the filters but can be set explicitly to run parallel watches, and that local selects the backend exactly as in search_catalog. It stops short of detailing start/end date grammar, deferring that to the sibling.

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 opening line states a specific verb and resource — 'Report only the acquisitions new since the last check of this site' — and immediately contrasts it with the full-list behavior of search_catalog. An agent can distinguish this delta tool from the plain search sibling 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?

It gives an explicit standing workflow (call, wait, call again, act only on the delta), tells the agent when to use reset=True to re-baseline, and tells it when to prefer local=false (live S3 walk catches freshly published passes). It also names search_catalog as the source of the filter grammar and points forward to change_composite / timescan as consumers.

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.