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

Annotations already declare read-only, idempotent and closed-world, so the description goes further by disclosing ranking logic (tier, then headline match, round-robin across the three publications), the match-tier vocabulary, paging via offset/next_offset, and the freshness caveat 'Facts are as of each item's date.' That is real behavioral context beyond the annotations.

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?

Purpose is front-loaded in the first clause and the rest is packed with payoff sentences about result shape and ranking. The ranking/tie-break sentence is long, but it is not padding — every sentence conveys a distinct fact.

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?

Output schema is absent, and the description verifies the return contract by listing id, title, URL with anchor, snippet, match tier plus reason, and citeAs. Ranking, paging and freshness are covered. Only minor gaps remain: no mention of empty-result behavior or limits on the query string beyond the schema's maxLength.

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%, so query, limit, offset and section are already documented; the description adds only the paging mechanic (offset/next_offset exists as a return field) and the implied per-publication scope. It does not add query syntax or limit-range meaning beyond what the schema states, so the 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 ('Keyword search') plus the exact resources covered (VI Update articles, Good Day, This Week, The Straight Record) and the scope option ('or one of them'). This clearly separates it from siblings like fetch, latest and list_items.

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?

'Use for finding coverage of a person, place, agency or event' gives an explicit use case, and 'Each result has an id for fetch' quietly routes the agent to the follow-up tool. There is no explicit when-not-to-use or comparison against latest/list_items for browsing recent items.

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