willow_institutional_search

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

Annotations only declare readOnlyHint, openWorldHint, and destructiveHint, all of which the description aligns with. The description adds substantial behavioral detail: the `ok`/`hits` protocol, source status fields, `max_results` vs `total`, the per-collection `limit_per_source` behavior, and required runtime credentials. No contradiction with annotations exists.

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?

The description is dense but every section earns its place: purpose, sibling distinction, response semantics, parameter caveats, and prerequisites. It is front-loaded with the most decision-relevant information and uses paragraph breaks to keep distinct concerns readable.

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 there is no output schema, the description compensates by describing the key result fields (`ok`, `hits`, `sources_queried`, `failed`, `skipped`, `timed_out`, `total`) and their meanings. It also covers required environments, the alternative tool, and parameter subtleties, making it complete for an agent to call correctly.

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?

The input schema has 0% field descriptions, so the description must carry the parameter documentation burden. It does well for `sources`, `max_results`, and `limit_per_source`, explaining cap semantics and fan-out behavior. However, `app_id` and `query` remain underexplained, and `query` is evident while `app_id` is not contextualized.

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?

The description opens with a specific verb and resource: 'Search ~60 named institutional and academic collections' with concrete examples. It explicitly distinguishes itself from the sibling tool with 'use `willow_web_search` for the open web,' so an agent can disambiguate immediately.

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?

The description gives explicit guidance: 'Use this when a claim needs backing; use `willow_web_search` for the open web.' It also explains when to narrow scope via `sources` and notes the required permissions, leaving little ambiguity about when to invoke this tool.

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