prepare_runs_diff

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

No annotations are provided, so the description carries full burden. It usefully states that no LLM call happens server-side, but does not disclose whether the tool is read-only, destructive, or requires authentication. Expected behavior beyond the main action is sparse.

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?

The description is two compact sentences that front-load the core action and then provide ordering and server-side behavior. No wasted words.

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 tool has 2 simple parameters and no output schema, the description covers the basic purpose and ordering. However, it does not describe the format of the returned structured data or the nature of the 'narrate instructions', leaving gaps for complex usage.

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?

With 0% schema description coverage, the description adds the semantics that run_id_a is the baseline (older) and run_id_b is the newer run. This adds meaning beyond the schema, but still lacks details on how to obtain these IDs or any constraints.

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 verb 'compute' and the resource 'regression / fix / coverage delta between two runs', and specifies it returns structured data and instructions. It distinguishes from siblings by mentioning the diff purpose.

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 explains that A is baseline and B is newer, providing ordering context. However, it does not tell when to use this tool over alternatives like prepare_coverage_gaps or prepare_run_summary, nor does it mention prerequisites or when not to use.

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