review_plan_revision

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered, but the description adds real value beyond them: it enumerates the validation rules enforced (each operation must trace to a finding or feedback), the lock categories respected, and the pass limit. The 'Read-only ... Records the plan in the session' pairing is slightly tense but internally consistent (session-level record, not project mutation), so it does not contradict the annotation.

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?

Three sentences, front-loaded with the action and artifact, then behavior, then destination. The middle sentence is long due to the enumerated lock categories, which is informative rather than wasteful, but it is the one spot that could be trimmed.

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 complex planning tool with a deep schema and an output schema (so return values need not be described), the description supplies the validation contract, the lock-respect guarantee, the pass limit, and the downstream handoff. It is essentially complete, with only prerequisites and failure behavior left implicit.

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 the sole top-level parameter ('request') carries its own description, so the schema does the heavy lifting. The description hints at the semantics of the enclosed operation list (traceability to findings/feedback, locks, pass limit) but adds no format or field-level detail beyond what the schema already documents; baseline 3 is appropriate.

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 artifact ('Compile one bounded revision plan') and names its inputs ('from evaluation findings and feedback'), which cleanly separates it from siblings like review_evaluate and review_apply_revision. An agent can place it in the review pipeline without opening the schema.

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 final sentence routes the agent forward ('Records the plan in the session for review_apply_revision'), establishing the ordering against the obvious alternative. It does not state prerequisites explicitly (e.g., that a review session and completed evaluation must already exist) or when-not-to-use, so it stops short of a 5.

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