Retest

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

Annotations already disclose the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower. The description adds useful mechanics, explaining that fast runs pre-commit-stage hooks and heavy runs pre-push-stage hooks (pytest, cargo, uv lock --check), but it omits side effects an agent would want, such as that hook runners may rewrite files and that jobs are submitted asynchronously.

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 verb and resource, with no filler. The only slight redundancy is the '(rm_gates)' parenthetical echoing the title, and the second paragraph re-explaining what the schema already spells out for `stage`.

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?

An output schema exists and the input schema is fully documented, so the description needn't cover return values. However, the schema's own parameter docs reference other actions ('status'/'explain'/'profile'/'audit_fail_fast'/'xdist_apply') that the description never acknowledges, leaving the agent unclear about whether this tool is retest-only or a multi-action dispatcher, and the escalate second-job behavior is never surfaced in prose.

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% and 12 parameters are each documented in the schema itself, including the full fast/heavy semantics of `stage`. The description only restates the stage behavior in prose and adds nothing about `escalate`, `dry_run`, `threads`, or `job_id` that the schema does not already cover, so the baseline 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 gives a specific verb+resource ('Retest ... Run and inspect the two-tier pre-commit gate across repos') and even distinguishes itself from the rest of the family with the claim that it is 'the single tool that can actually drive both tiers'. That differentiates it conceptually from siblings like rm_gates_status/explain/profile, though it never explicitly names rm_gates_run, which an agent would most plausibly confuse it with.

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?

Usage is only implied: the name and the two-tier explanation suggest this is used to re-run failed hooks, but there is no statement of when to choose retest over rm_gates_run, status, or explain, and no prerequisites or exclusions. The stage paragraph is invocation guidance rather than selection guidance.

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