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

Annotations already declare the mutation/idempotency/safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds genuinely useful context beyond them: the write is delegated to a local agent and the server persists only 'bounded metadata and an attested outcome', which tells the agent about data retention scope. It could still say more about failure/timeout behavior on the agent round-trip.

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?

A single dense sentence with no filler; the core action is front-loaded. The trailing clause about storage is compact and informative, though the sentence is a touch information-packed.

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 mutating tool with no output schema and a six-parameter nested schema, the description covers storage semantics but omits the local-agent prerequisite, the meaning of auxiliary IDs, and any error/failure behavior. Annotations carry the safety profile, so this is adequate but with clear gaps.

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 and the description offers no additional parameter meaning (no mention of idempotencyKey reuse, projectId provenance, or the bounded nested metadata). Note the schema's own descriptions are partly copy-pasted and misleading for reviewId/sessionId/executionId/status, but the description does nothing to compensate.

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+resource ('create local change review') and adds a distinguishing detail — that the action is delegated to a connected local agent rather than handled purely server-side. It does not name the close siblings (get_change_review, list_change_reviews, refresh_local_change_review), so the differentiation is implied by the verb rather than explicit.

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 phrase 'connected local agent' hints at a prerequisite (a local agent must be connected), but the description never states when to use this tool versus refresh_local_change_review, get_change_review, or list_change_reviews, nor any conditions/exclusions. Guidance is at best implied.

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