Diff two runs' outputs

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds valuable context: secrets are masked by default, the tool never re-runs anything (read-only), and identical outputs return a note. This disclosure exceeds what annotations alone provide.

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 concise yet complete, structured with a clear opening statement followed by behavioral details and parameter explanations. Every sentence adds value without redundancy.

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 no output schema, the description explains the return format (unified diff, plain text) and includes a note for identical outputs. It covers all key aspects: use cases, default behavior, error conditions, and security masking, making it fully informative.

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% with descriptions for each parameter. The description adds context for the 'id' parameter (explains -N syntax) and clarifies 'other' as the older side. While baseline is 3 due to high coverage, the extra semantics justify a 4.

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 tool produces a unified diff between two runs' outputs. It distinguishes from siblings like get_output (which returns full output) and search_output/list_commands (different purposes), making the tool's purpose specific and unambiguous.

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?

Explicit guidance on when to use with only 'id' (diffs against previous same command) versus with 'other' (explicit pair). It also explains error conditions (no earlier identical command line) and behavior for identical outputs, fully guiding the agent's decision.

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