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

Annotations only declare readOnlyHint, so the description carries most of the burden and does disclose the response content (identity, sector, identifier sources, rollup counts) for a tool with no output schema. It omits pagination behavior even though limit/offset exist, and does not state result ordering beyond 'catalog held first' for the state mode.

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?

Three dense sentences, no filler, and the primary input (name fragment or UNITID) is front-loaded. The second sentence is a long compound clause that takes a second read, which keeps it from a 5.

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 no output schema, the description sensibly summarizes the returned fields and the three input-driven result modes. Pagination and the city refinement are left entirely to the schema, which is acceptable given 100% schema coverage but leaves a small gap for a five-parameter tool.

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 the baseline is 3. The description reinforces the query parameter (name fragment or UNITID) and the meaning of a state answer, but it never explains the city parameter or the offset/limit contract, adding little beyond the schema.

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 names concrete inputs (name fragment, IPEDS UNITID, state) and the concrete payload it returns (identity, sector, identifiers with sources, counts of programs/checklists/learning units). It is clearly a discovery/lookup tool, but it never distinguishes itself from the sibling get_institution, so an agent must infer that find_institution resolves fragments while get_institution fetches by known id.

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?

It maps each input combination to an outcome: name/UNITID gives one identity, a state gives that state's institutions, and no name plus no state gives the states with counts. That is explicit contextual guidance, though it stops short of naming an alternative tool or stating when-not to use it (e.g., when the id is already known, use get_institution).

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