Compare two runs

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds little beyond restating the defaults already in the schema, and leaves open behavioral questions such as what threshold makes a duration change 'significant' and how large the returned diff can get.

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, front-loaded with the verb and the enumerated diff categories, and the default behavior stated last where it lands as a useful aside. No filler.

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?

For a parameterless-by-default read-only diff tool with a fully documented schema, the description is nearly complete. The only real gap is the undefined 'significant duration changes' threshold, plus no hint of the response shape since there is no output schema.

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 both parameters document accepted forms (run id, build number, commit prefix, 'latest'/'previous'). The description's 'defaults to previous vs latest' merely repeats what the schema already states, so the baseline of 3 applies.

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 names a concrete verb (diff) and resource (two runs) and enumerates the exact output categories: newly failing, fixed, still failing, added/removed tests, and duration changes. That is far more specific than a generic 'compare' but it never names a sibling such as detect_regressions, which an agent might plausibly choose instead for overlapping needs.

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 default ('previous vs latest') gives the agent useful context for calling it with no arguments, so usage is implied. However, there is no explicit statement of when to prefer this over detect_regressions or get_run_summary, and no exclusions are offered.

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