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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), but the description adds substantial non-structured behavior: the state guard, the side effect ('Records one activity event with the user'), account/credential restrictions, conflict-on-invalid-state, and a non-idempotency warning that retrying after uncertain delivery may double-write or fail the state guard. That retry hazard is exactly the kind of detail annotations cannot express.

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 core action and the strongest disambiguation before moving to state, side effects, and retry guidance. Nearly every clause carries distinct information, though the semicolon-chained sentences pack several ideas into single lines, which slightly hurts scannability.

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 state-mutating tool with an output schema, the description still usefully notes the return shape (bounded evidence entries and prompt references, cursor continuation) and covers preconditions, side effects, failure mode, and retry semantics. Nothing an agent needs to invoke it 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 already name their upstream source tools (list_sites_and_topics, get_recommendations), so the schema carries the parameter burden. The description adds no additional meaning about siteId or recommendationId beyond the state conditions, so 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?

States a specific verb+resource ('Record that the user has put the recommended work live') and immediately scopes it against siblings by denying two adjacent interpretations: 'it does not publish website content or trigger a Scan.' An agent can separate this from trigger_scan and from create_recommendation_action 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 explicit preconditions ('Requires approved or underway and no publication date'), explicit exclusions, and explicit recovery routing ('inspect get_recommendation before retrying'). It also names the alternative to use for continuation ('continue non-null cursors using get_recommendation'), so both when-to-use and when-not are covered.

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