Skip to main content
Glama

Manage watchlist

manage_watchlist
Destructive

Not affiliated with the U.S. government, GSA, or SAM.gov. Not a U.S. government service. Watch or pass on a contract or grant opportunity. Watching saves it to your list. Passing records why, so patterns emerge over time. Changes require applicable write access. Standard dynamically registered OAuth clients are read-only; approved OAuth write clients also require your explicit consent. Follow-ups within 30 minutes after a search ride free (up to 30 per search); otherwise one accepted call counts as one use.

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": {
      "action": "<action>"
    },
    "name": "manage_watchlist"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoOptional note with the pass reason
limitNoMaximum 100 records; minimum 1; default 50.
actionYeswatch, pass, unwatch, unpass, list, or remove_legacy
cursorNonext_cursor from the previous watchlist page
reasonNoWhy passing (required for pass): wrong_fit, too_small, too_large, bad_timing, incumbent_locked, location, other
notice_idNoThe contract notice ID or grant opportunity number (required for mutations)
legacy_keyNoOpaque legacy_key returned for an unresolved old save; remove_legacy only
record_typeNoSource record type. Required when IDs overlap; widget always supplies it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / limit / description
      Added value: +"Maximum 100 records; minimum 1; default 50."
  2. Changed6 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"watch, pass, unwatch, unpass, or list"New value: +"watch, pass, unwatch, unpass, list, or remove_legacy"
    • addedInput schema / properties / cursor
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 1024,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "next_cursor from the previous watchlist page",
      +  "title": "Cursor"
      +}
    • addedInput schema / properties / legacy_key
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 64,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Opaque legacy_key returned for an unresolved old save; remove_legacy only",
      +  "title": "Legacy Key"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 50,
      +  "maximum": 100,
      +  "minimum": 1,
      +  "title": "Limit",
      +  "type": "integer"
      +}
    • changedInput schema / properties / notice_id / description
      Previous value: -"The notice ID (required for watch/pass/unwatch/unpass)"New value: +"The contract notice ID or grant opportunity number (required for mutations)"
    • addedInput schema / properties / record_type
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "contract",
      +        "grant"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Source record type. Required when IDs overlap; widget always supplies it.",
      +  "title": "Record Type"
      +}
  3. First observed

TDQS

B3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint false, destructiveHint true, idempotent false), the description discloses real operational context: write access is required for changes, standard dynamically registered OAuth clients are read-only, write clients need explicit consent, and there is a per-search quota of 30 free follow-ups. It does not say which action is destructive or whether unwatch/remove_legacy can be undone, which is the main remaining gap.

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

Conciseness2/5

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

Three sentences of legal disclaimer ('Not affiliated with the U.S. government...') precede the actual purpose, so the useful content is not front-loaded. The remainder is compact enough, but an agent scanning the first lines gets no actionable signal.

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

Completeness2/5

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

An eight-parameter, six-action mutation tool with no output schema needs prose to cover the action set, pagination, and the destructive path; the description covers only two of six actions and never mentions list, cursor, limit, or remove_legacy/legacy_key. Given destructiveHint=true, the absence of any statement about what gets removed is a notable omission.

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 all eight parameters are already documented, including reason and note; the description only adds motivation ('so patterns emerge over time'). It says nothing about the cursor/limit pagination used by the list action, so it adds little beyond the schema.

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

Purpose3/5

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

The description covers only 'watch' and 'pass' with concrete effects ('Watching saves it to your list', 'Passing records why'), but the action parameter also allows unwatch, unpass, list, and remove_legacy, none of which the description explains. An agent cannot learn from prose what 'unwatch' vs 'remove_legacy' does, so intent is only half conveyed.

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

Usage Guidelines3/5

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

It implies when to watch vs pass (save vs record a reason) and adds a practical usage rule about follow-up calls within 30 minutes being free. But there is no guidance on choosing 'list' over a search tool, no prerequisites for the destructive actions, and no stated alternatives among the many sibling search tools.

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.

Resources