scorecard_search

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's a safe, non-destructive read operation. The description adds that it returns data from the College Scorecard but doesn't disclose any other behavioral aspects like rate limits, pagination details beyond per_page, or that results may be partial matches. This is adequate but not rich.

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 two short paragraphs. The first states purpose and return data, and the second lists search and sort options. It is front-loaded with the core purpose art=true. Each sentence earns its place, though it could be slightly more concise by merging the lists.

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?

For a search tool with no output schema, the description does a good job of explaining what data is returned and what parameters are available. It doesn't mention pagination beyond per_page, but that is covered in the schema. The tool's complexity is moderate (5 optional params), and the description covers usage adequately. The absence of output schema is not a major gap since the return fields are listed.

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 each parameter already has descriptions in the schema. The description adds context by listing the search dimensions (name, state, school type) and sort fields (cost, earnings, graduation rate) which map to the schema's parameters, but goes beyond by clarifying that name is a partial match and sort values are specific schema paths. This adds meaning 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 clearly states it searches U.S. colleges and universities from the College Scorecard, and lists specific return fields (tuition, admission rate, graduation rate, median earnings, student debt). It also explicitly mentions search dimensions (name, state, school type) and sort options, making its purpose distinct from sibling tools like scorecard_compare and scorecard_top.

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 clear guidance on what the tool does and how to filter (by name, state, school type) and sort. It does not explicitly mention when NOT to use this tool versus siblings, but the context from the description (search plus sort) implies this is the general search tool, while siblings like scorecard_compare and scorecard_top likely have more specific use cases.

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