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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral detail — results carry provenance and the cursor is generation-pinned, meaning pagination is stable against index changes — which is exactly the kind of context annotations cannot convey.

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?

Two sentences, no filler. The scope of searchable collections comes first and the result-shape note second, which is the right front-loading order.

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?

With an output schema present and full schema coverage, the description needn't explain return values, and it correctly restricts itself to the pagination/provenance caveat. The one missing piece is routing guidance versus the specialized search_* siblings, which matters given how many of them exist.

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%, so q, limit, cursor, and collection are all documented in the schema, establishing the baseline of 3. The description's collection enumeration mirrors the schema's own examples and adds no syntax, format, or defaulting detail beyond it.

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 (search) and enumerates the resource families it covers (opportunities, vendors, awards, exclusions, reference collections), which is far more informative than the bare name. It doesn't differentiate itself from the specialized siblings search_opportunities and search_exclusions, so an agent can't tell from this text alone whether this is the general-purpose entry point or a duplicate.

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?

Usage is only implied by the collection list: it hints that this tool spans multiple collections, while the siblings are collection-specific. There is no explicit 'use this when searching across collections' or 'prefer search_opportunities for opportunity-only queries' statement, and no prerequisites or exclusions are given.

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