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

Far exceeds the annotations (readOnly=false, destructive=true, idempotent=false): it discloses the state guard, conflict-on-invalid-state refusal, that exactly one activity event is recorded with the user, that history is retained, and that retrying after uncertain delivery can fail the guard or duplicate an event after intervening moves.

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-loads the operation and its state effect, then layers side effects, error behavior, and retry guidance in a logical order. Dense but nearly every sentence carries distinct operational weight; only the movement/reason phrasing is slightly redundant.

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?

Given a mutation tool with an output schema and full schema coverage, the description still supplies the missing behavioral context: state guard, conflict semantics, event recording, truncation limits on returned evidence/prompt references, and non-idempotent retry hazards. Nothing needed to call it safely is absent.

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 coverage is 100% and both parameters (siteId, recommendationId) are documented in the schema itself, so the baseline is 3. The description adds no argument-level detail beyond naming get_recommendation as the source of the recommendationId cursor.

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 (decline) and resource (recommendation), plus the exact resulting state transition: archived with declined movement and archive reason declined. An agent can distinguish this from approve_recommendation, archive_recommendation, and restore_recommendation 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?

Clearly scoped to recommendations 'in review' and explicitly routes the agent to get_recommendation for cursor continuation and post-failure readback. It does not, however, explicitly contrast with the closer sibling archive_recommendation, so the choice between decline vs. plain archive is left to inference.

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