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

With only readOnlyHint=true given, the description carries the behavioral load and does so richly: it discloses what each major returns, that words resolve through the KSA Dictionary and never by spelling match, that unmatched words return the closest Dictionary terms, that award-level completers flags are per-field and never summed, and that per-school IPEDS rows are not published (state count only). This is substantive disclosure well 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?

It is front-loaded with the driving question and the two input paths, then layers behavioral detail. The single long middle sentence is dense and somewhat baroque, but nearly every clause conveys behavior an agent can use, so the length is largely earned rather than padding.

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 six-parameter tool with an output schema, the description supplies the resolution logic, fallback behavior, and data-scope caveats an agent needs to call it correctly, and it need not restate return values. The only gap is the absence of explicit routing to sibling tools for adjacent tasks.

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 coverage is 100%, so baseline is 3, but the description adds real meaning: 'words' resolve semantically via the KSA Dictionary (not literal matching), 'soc' pulls every crosswalk-linked major, and 'state' affects the stated school count rather than raw rows. It clarifies the semantics of the otherwise terse schema fields.

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+resource (find the majors answering a study question) and spells out the two input modes: a person's own words or a SOC job code. It is clearly distinct from lookup-style siblings such as find_programs or find_institution, but it never names an alternative tool explicitly, so it stops short of full sibling routing.

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 opening framing ('What should I study?') implies the use case and the accepted inputs, and the resolution rules hint at behavior. However, there is no explicit when-to-use / when-not, no prerequisites, and no pointer to alternatives like compare_my_major for side-by-side comparison, so guidance is only implied.

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