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

With no annotations, the description carries the full burden and does well: it discloses that outputs are tail-truncated and why (failure summaries sit at the end, install noise at the start), that diffs are path+line counts rather than content, and that the LLM trace is conditional ('when available'). It does not describe failure behavior for an unknown/mismatched run id, leaving one behavioral 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?

Three dense sentences with the primary return value front-loaded and parenthetical caveats kept tight; every clause carries information (truncation rationale, alternatives, trace fields). Slightly overloaded with nested asides, but no filler sentences.

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?

With no output schema, the description does the heavy lifting by enumerating the return payload (fix diff, before/after test output, per-LLM-call trace with stage/model/status/latency) and the files alternative. Only error/edge conditions and any size or pagination behavior remain unstated.

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 coverage is 100% and the schema description already spells out 'the triage run id, as returned by get_triage_runs ... not the build id or issue number'. The description restates the same disambiguation in the parameter's context, adding emphasis rather than new meaning. Baseline 3 is appropriate 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.

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

States a specific verb+resource ('Returns the generated fix diff ... and before/after test-run output for one triage run') and immediately differentiates itself from siblings by naming get_triage_runs (id source) and get_build_files (full contents). An agent can distinguish it from get_test, get_build, or get_build_files without opening any schema.

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?

Gives explicit preconditions and anti-patterns: the id must come from get_triage_runs and is 'NOT a build id and NOT an issue number', and it routes to get_build_files for full file content. It stops short of stating when this tool is unnecessary (e.g. when the run is still in progress or when only a build-level view is wanted), so it is strong but not fully exhaustive.

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