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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorld, so the safety profile is covered. The description adds no behavioral context beyond that, and in fact the '2-5 schools' limit merely restates the schema's minItems/maxItems rather than disclosing behavior such as what happens with invalid UNITIDs or partial data.

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, front-loaded with the comparison scope, and zero filler. Every clause earns its place.

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 usefully names what is compared (cost, outcomes, admissions), giving the agent a sense of the response. It is nearly complete for a simple one-parameter comparison tool, missing only return-shape details like metric granularity.

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% with a single well-documented parameter (2-5 IPEDS UNITIDs), so the baseline is 3. 'Pass UNITIDs' adds no syntax, format, or source information beyond what the schema already states.

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 (side-by-side comparison) and resource (schools) plus the metric categories covered, which separates it from single-school siblings like college_metrics or college_demographics. It does not explicitly name the sibling tools, so it falls short of a 5.

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 instruction 'Pass UNITIDs' implies UNITIDs must already be known, hinting that a lookup step precedes this call, but there is no explicit when-to-use guidance or reference to college_search as the way to obtain IDs. Usage is only implied.

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