Skip to main content
Glama

Report whether a lookup fix worked

close_lookup
Idempotent

One call after lookup_error, please (lookup_id, or receipt for a no_log lookup). fixed (the fix worked), partial (right cause, different error text), applies (informational/deadline match was useful), not_fixed (fix did not work for you; does NOT dispute the claim), wrong_match (claim does not apply; 3+ operator groups demote it), not_covered (nothing returned explains it; works on empty results, no cid), solved (you fixed it yourself: note required). Counted once per operator group. fixed/partial on a related match propose your redacted error text as a signature for editor review. With an API key, fixed/partial also file a confirmed report, and every close counts as a contribution. Fail open: if Breakwire is slow, down or returns nothing, continue with the original task; never block on it.

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": {
      "outcome": "<outcome>"
    },
    "name": "close_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
cidNoone of the returned claims; omit for not_covered/solved
noteNowhat fixed it / what happened; secrets are stripped; up to 500 chars (longer is cut and named in clipped[])
outcomeYes
receiptNorc_... from a no_log lookup (persistence.receipt): closes it without the error text ever being stored
lookup_idNolk_... from a logged lookup
evidence_typeNowhat you observed; fixed defaults to remedy_tested (you applied the fix and the call worked)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / note / description
      Added value: +"what fixed it / what happened; secrets are stripped; up to 500 chars (longer is cut and named in clipped[])"
  2. Changed4 schema fields changed
    • addedInput schema / properties / evidence_type
      Added value: +{
      +  "description": "what you observed; fixed defaults to remedy_tested (you applied the fix and the call worked)",
      +  "enum": [
      +    "source_checked",
      +    "applicability_checked",
      +    "failure_reproduced",
      +    "remedy_tested",
      +    "production_recovered"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / lookup_id / description
      Added value: +"lk_... from a logged lookup"
    • addedInput schema / properties / receipt
      Added value: +{
      +  "description": "rc_... from a no_log lookup (persistence.receipt): closes it without the error text ever being stored",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "lookup_id",
      -  "outcome"
      -]New value: +[
      +  "outcome"
      +]
  3. Changed2 schema fields changed
    • addedInput schema / properties / cid / description
      Added value: +"one of the returned claims; omit for not_covered/solved"
    • changedInput schema / properties / outcome / enum
      Previous value: -[
      -  "fixed",
      -  "not_fixed",
      -  "wrong_match",
      -  "solved"
      -]New value: +[
      +  "fixed",
      +  "partial",
      +  "applies",
      +  "not_fixed",
      +  "wrong_match",
      +  "not_covered",
      +  "solved"
      +]
  4. Changed1 schema field changed
    • changedInput schema / properties / outcome / enum
      Previous value: -[
      -  "fixed",
      -  "not_fixed"
      -]New value: +[
      +  "fixed",
      +  "not_fixed",
      +  "wrong_match",
      +  "solved"
      +]
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare mutation, idempotency and non-destructiveness; the description adds real behavioral context beyond that — counting is once per operator group, wrong_match demotion after 3+ operator groups, signature proposals for editor review on fixed/partial, a confirmed report filed when an API key is present, and contribution accounting. Some of this is jargon-heavy and under-explained ('3+ operator groups demote it', what a 'confirmed report' entails), so the disclosure is substantial but not fully legible. This is well past the annotation bar.

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?

It is compact but reads as a run-on chain of parentheticals, mixing outcome semantics, side effects, auth behavior and fail-open policy in one block. Every clause is roughly useful, yet the lack of grouping (outcomes here, consequences there, resilience last) forces re-reading. The conversational 'please' and 'for you' add no selection value.

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

Completeness4/5

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

For a 6-parameter mutating tool with no output schema, the description covers the hardest parts: which identifiers are valid, conditional note requirements, side effects of filing reports, and failure-mode behavior. What it omits is what the agent gets back on success (confirmation, any returned signature id) and what happens on an invalid cid, which matters given there is no output schema to lean on.

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 83%, so descriptions of cid/note/receipt exist in the schema. The description still adds conditional logic the schema does not: lookup_id vs receipt as mutually exclusive paths for logged vs no_log lookups, and the requirement of a note for the solved outcome. That extra routing information justifies a step above the baseline 3.

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

Purpose4/5

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

The title and the phrase 'One call after lookup_error' plus the full outcome enum make it clear this tool records the result of a prior lookup and closes it out. It distinguishes itself from the sibling lookup_error by sequencing rather than by an explicit contrast statement. A crisp lead sentence such as 'Close a lookup by recording its outcome' is implied rather than stated, keeping it just below a 5.

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

Usage Guidelines4/5

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

Timing is given explicitly ('One call after lookup_error'), and each outcome value carries a parenthetical condition (e.g. 'not_fixed (fix did not work for you; does NOT dispute the claim)', 'solved (you fixed it yourself: note required)') so the agent can pick the right one. The fail-open instruction tells the agent when NOT to wait on the tool. No explicit alternative tool is named for cases where the agent should skip closing entirely, which keeps it at 4.

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