Verify "done"

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

Annotations already indicate non-read-only, open-world, and non-idempotent behavior. The description adds valuable context by specifying the exact PASS/FAIL logic (test exit 0 plus all expect_changed paths appearing in git status) and the conditional git diff behavior. It does not contradict annotations and goes beyond what annotations 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 three sentences, front-loaded with the core purpose, followed by the mechanism and a memorable metaphor. Every sentence earns its place with no redundancy or filler. Excellent structure.

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's complexity (5 parameters, output schema, annotations), the description covers the essential behavior: running tests, diffing changes, and the PASS condition. It correctly omits output schema details since an output schema exists. Minor gaps like handling non-git repos are implicitly covered ('if the directory is a git repo'). Complete enough for an agent to select and invoke correctly.

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%, so the baseline is 3. The description adds significant meaning to 'expect_changed' by explaining that each claimed path must appear in git status for PASS, and clarifies the role of the test command. This goes beyond the schema's simple field descriptions, justifying 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's purpose: proving a task is complete by running tests and diffing changes. It uses a specific verb ('prove'), names the resource (task completion), and provides a vivid metaphor ('the gate between agent says done and I believe it'). While it doesn't explicitly distinguish from the sibling 'check_repro', its purpose is unambiguous and specific enough to stand alone.

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 clearly conveys when to use this tool: any time you need to validate an agent's 'done' claim. It provides strong context through the gate metaphor, but does not explicitly mention alternatives or exclusion criteria (e.g., when to use check_repro instead). Given clear context without exclusions, this aligns with a 4.

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