willow_institutional_search

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

The description reveals important behavioral details: every hit carries confidence:'institutional' because a named collection was queried, not hostname reputation. It defines the `ok` flag's semantics and explains that `limit_per_source` is per collection, not overall, which can produce more hits than `max_results`. It also states access requirements (web_net, consent.internet, live egress lease), adding context beyond the readOnlyHint annotation.

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 organized, with each sentence adding value: purpose, alternative, response semantics, parameter effects, and requirements are covered in four concise paragraphs. No fluff or repetition exists; it's front-loaded with the core purpose.

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 no output schema, the description covers return values (`ok`, `hits`, `total`, source statuses) and failure modes thoroughly. However, it omits the structure of individual hits and the meaning of `app_id`, leaving gaps in a tool with 5 parameters and a complex return set. Still, most operational context is provided.

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 schema provides zero parameter descriptions (0% coverage), so the description must compensate. It explains `sources`, `max_results`, and `limit_per_source` clearly, including the distinction between `max_results` and `total`. However, the required `app_id` parameter is never mentioned, and `query` is only implicitly understood as the search term, leaving a gap in guidance.

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 begins with 'Search ~60 named institutional and academic collections' and lists examples, providing a specific verb and resource. It also distinguishes from sibling `willow_web_search` by saying 'use `willow_web_search` for the open web.'

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 sentence 'Use this when a claim needs backing; use `willow_web_search` for the open web' explicitly gives when-to-use and an alternative. It also provides operational guidance like checking `ok` before `hits` and interpreting `sources_queried`, `failed`, `skipped`, `timed_out`.

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