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

Goes well past the annotations: it narrows the scope of destructiveHint=true to just the archive date and reason, confirms approval/publication/readiness history is preserved, discloses the side effect of one activity event, notes account/credential restrictions, and explains that idempotentHint=false means repetition can hit a state guard or duplicate an event.

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 core action and the precise destruction scope, and every sentence carries operational content. The final retry sentence is dense but justified; the description is on the long side for a two-parameter tool.

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?

Despite an output schema existing, it usefully adds the pagination contract (ten evidence entries, ten prompt references, continue non-null cursors via get_recommendation) and the conflict/retry behavior, so an agent has everything needed to call it safely.

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 are documented in-schema with their source lookups (list_sites_and_topics, get_recommendations), so the description adds nothing about siteId or recommendationId. 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 and resource ('Restore an archived recommendation') plus the resulting state change ('to review with new movement'), which cleanly separates it from archive_recommendation and start_recommendation_work among the siblings.

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 a clear retry protocol — inspect get_recommendation after uncertain delivery or readback failure — and names that sibling, plus the condition under which the call is refused (invalid state/conflict). It does not, however, state when an agent should prefer archiving or other lifecycle tools instead.

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