correlate_ids

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It implies the tool mutates no state ('extract and rank' is read-only) but doesn't explicitly state it's non-destructive. More importantly, it doesn't disclose what happens if evidence_snippets contains no shared IDs, how ranking works, or whether it has side effects. For a tool with no annotation coverage, this is a notable gap.

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

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

Two sentences with zero waste. The core action is stated first, followed by a concrete use case. Every word earns its place, and it's appropriately sized for a simple tool.

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

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

Given the simplicity (one required param, no output schema, no annotations), the description is mostly complete for calling the tool. It covers what it does and when to use it. However, it lacks detail on the output format (what 'rank' means) and edge cases (e.g., empty input), which would be useful but not critical. It's adequate but could be enhanced.

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

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but there's only one parameter, evidence_snippets, and the description clarifies it means log snippets already collected elsewhere. This adds meaning beyond the mere array-of-strings type. However, the description doesn't clarify expected format (e.g., raw log lines vs. structured JSON), which would help. Baseline 3 is appropriate given the single parameter and minimal description coverage.

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

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

The description clearly states the action (extract and rank correlation IDs) and the resource (correlation IDs across log snippets), and it gives a concrete example use case (sync-to-async hop). This distinguishes it from the listed siblings, which are investigation planning, visual evidence analysis, querying sources, coverage, and RCA validation. However, it does not explicitly name a sibling to contrast with, and the verb 'correlate' is slightly less specific than 'extract and rank.'

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

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

The description provides context on when to use it: when you have log snippets already collected and need to carry an identifier forward across an async hop. It implies it's for analysis after evidence collection, differentiating from query_generic_source and list_generic_sources which are for gathering sources. However, it doesn't explicitly say when NOT to use it or mention alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.