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

Annotations flag destructiveHint=true and idempotentHint=false; the description goes well beyond them by explaining exactly what changes (clears the review flag, moves needs_review to stable, preserves other movement and board column), that invalid state returns conflict, that one activity event is recorded, and that repetition can fail a state guard or create a duplicate event. That is substantial non-idempotency and safety context an agent could not derive from the annotations alone.

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?

Front-loaded with the action and its precondition; every sentence carries distinct operational content (state guard, activity event, auth restrictions, cursor handling, retry procedure). It is dense and long, and the retry sentence in particular is packed, but nothing is filler.

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 mutation tool with a state guard, this covers preconditions, allowed failure mode (conflict), event side effect, auth restrictions, cursor handling, and retry-after-failure procedure; return-value shape is backed by an output schema. Nothing an agent needs to call this correctly is missing.

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 both parameters are fully documented in the schema (siteId from list_sites_and_topics, recommendationId from get_recommendations), so the baseline is 3. The description adds only the needsReview precondition rather than parameter-level detail.

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 precise verb+resource ('Acknowledge the recommendation review flag') and immediately scopes it against the obvious confusable sibling with 'This does not approve the recommendation.' An agent can distinguish it from approve_recommendation, decline_recommendation, and start_recommendation_work without opening any 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?

Gives an explicit precondition (needsReview=true), an explicit non-use case (does not approve), and routes the agent to get_recommendation both for cursor continuation and for readback after uncertain delivery. It even names when to inspect before retrying rather than retrying blind.

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