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

Annotations include readOnlyHint=true, which signals that the tool is safe and non-mutatingley. The description adds useful context about the output fields (checklist IDs to pass to get_checklist), which helps the agent understand the data flow. However, it does not disclose other behavioral details such as pagination behavior (though the offset parameter and limit suggest pagination), rate limits, or any potential large response sizes. The description does not contradict the annotations, so a 3 reflects that it partially compensates beyond the 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 a single, information-dense sentence that lists the outputs and the connection to get_checklist. It is concise and front-loads the core question ('What programs does this institution publish?'), making it easy for an agent to scan. It loses one point because it might be slightly packed with technical terms (CIP, credential class) that could be clarified, but overall it 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?

Given the complexity (multiple fields returned, relationship to checklists, pagination via offset), the description provides enough context to understand the tool's role. The output schema is absent, so the description's enumeration of returned fields partially compensates. However, it does not explicitly mention pagination behavior or the possibility of multiple pages, which is relevant given the limit and offset parameters. An agent might need to infer they should use the returned next_offset to fetch all results. This is a minor gap, so a 4 is appropriate.

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 schema already explains each parameter: unitid is the institution's IPEDS ID, query filters by program/award words, limit sets page size, and offset is for pagination. The description adds minimal extra meaning about parameters; it mentions 'checklist ids to pass to get_checklist' but that's output-related, not param-specific. Since the schema does the heavy lifting, the description's contribution is marginal, hence a baseline 3.

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 clearly specifies the purpose: listing programs an institution publishes, and enumerates the exact fields returned (award, credential class, CIP, published credit figure, catalog edition, captured page, checklist IDs). It distinguishes this tool from siblings by focusing on institution-level program data, whereas siblings like get_checklist or certifications_for_program target different resources.

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 implies usage: when you need programs for an institution male. However, it does not explicitly state when NOT to use this tool, nor does it mention alternatives among the siblings. For example, it does not say 'use certifications_for_program for certifications' or mention any exclusions. The context is clear for institution-level program lookup but lacks explicit guidance on choosing among similar tools.

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