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

With no annotations, the description carries the burden and does well: deterministic, no LLM, no network, message-only scanning, batch cap, and the large-commit threshold derived from caller-supplied insertions/deletions. It does not disclose the shape of the returned findings, which is a remaining gap given there is no output schema.

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?

Dense but front-loaded with the tool's identity followed by the checklist and the message-only scope caveat. It reads as one long run-on sentence, but nearly every clause adds a distinct check or constraint, so little is wasted.

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 multi-check validator with no annotations and no output schema, the description omits the return format: whether findings are a list, how severity is reported, or what a clean result looks like. Input semantics are complete, but an agent cannot anticipate the response shape.

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 baseline is 3, but the description adds real meaning: max_lines_changed is a threshold on insertions+deletions that triggers a large_commit finding, and insertions/deletions are caller-supplied rather than computed. It also clarifies the commit vs commits alternative and the batch ceiling.

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?

States a specific verb and resource (commit-message hygiene checker) and enumerates the exact checks it performs: conventional format, vague subjects, subject length, secret patterns, oversized commit. This clearly separates it from siblings like pr_description_lint and regex_lint, which operate on different artifacts.

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?

Gives clear operating context: POST one commit or a batch up to 200, and explicitly scopes the secret scan to message text, never a diff. It does not, however, state when to prefer this over a sibling linter or any prerequisites/exclusions for use.

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