Audit Fail Fast

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is largely covered; the description adds useful behavioural detail (what the heavy stage actually executes, per-repo timeout, parallel workers, the 'escalate' second-job rule for retest, and the deliberate dry_run=true default for config rewrites). It does not, however, reconcile the write-capable xdist_apply/config-rewrite behaviour it describes with readOnlyHint=true, leaving a latent tension rather than a clean disclosure; no return/pagination detail is needed given the output schema exists.

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 short paragraphs, front-loaded with the purpose and the stage distinction, with no filler sentences. Minor penalty because the second paragraph duplicates the schema's own 'stage' description almost word-for-word, spending description budget on information the agent already receives from the schema.

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?

With an output schema present, return values need not be described, and the two-tier gate concept is conveyed. But the definition is muddled for invocation: parameter descriptions reference operations from other tools (status/explain/profile/run/retest/xdist_apply, plus a dangling 'phase_direction_here' placeholder) without clarifying which of these this tool actually performs, and it never explains what 'fail fast' auditing means or the default operating scope.

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 description coverage is 100%, so the baseline is 3: every parameter is already documented in the schema and the description mostly restates the stage semantics verbatim. It adds little parameter meaning beyond the schema (it does not clarify repo vs repos vs fleet interplay or scope defaults), so it neither compensates for nor improves on the structured data.

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 concrete verb+resource: it runs and inspects the two-tier (fast/heavy) pre-commit gate across repos, and even claims to be 'the single tool that can actually drive both tiers', which is a differentiation claim against the rm_gates_* family. However it never names the sibling it competes with (rm_gates_run, rm_gates_retest), and the surrounding text blurs the tool's identity by describing modes (status/explain/profile/run/retest/xdist_apply) that belong to other tools, so an agent cannot cleanly tell what THIS tool does by default.

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?

It explains stage semantics well ('fast' -> pre-commit-stage hooks/formatters, 'heavy' -> pre-push hooks such as pytest/cargo/uv lock --check), which is real usage guidance for parameter selection. But there is no when-to-use-this-tool-vs-alternatives guidance: siblings rm_gates_run, rm_gates_retest, rm_gates_status, rm_gates_explain and rm_gates_profile are never mentioned and no exclusion is stated. Guidance is implied rather than explicit.

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