compare_runs

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

The description adds valuable behavioral context beyond the readOnlyHint annotation by disclosing what the tool does NOT return (raw evidence, result_detail, error_record). This helps the agent set expectations and avoid misusing the tool. The readOnlyHint is consistent with a read-only comparison operation.

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 sentences long, front-loaded with the core purpose, and every word adds value. The second sentence is a crisp exclusion that prevents misinterpretation. No fluff or repetition of schema details.

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?

The description, combined with the output schema, covers the core semantics well: what the tool does and what it excludes. However, it does not clarify the limit parameter's role (e.g., 'limits number of comparison items returned'), which is a minor gap. For a tool with this complexity, the description is nearly complete but not perfect.

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 must compensate. It hints that base_run_id and target_run_id are the two runs being compared, but it does not explicitly name them or explain the limit parameter. The description adds minimal meaning beyond the parameter names themselves, leaving the agent to guess at limit's behavior.

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 uses the specific verb 'Compare' followed by the resource 'summary result changes' and the scope 'between two runs.' It also explicitly differentiates from sibling tools by stating 'Not raw evidence; no result_detail or error_record,' which distinguishes it from get_result_detail and get_failed_tests.

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 gives clear context that this tool is for comparing summary-level results, not raw evidence or errors. While it doesn't explicitly name alternative tools, the exclusion of result_detail and error_record implicitly steers users toward get_result_detail or get_failed_tests when those are needed. This is clear enough but not fully explicit.

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