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

With no annotations provided, the description carries the full burden and does substantial work: it names sources, states that O*NET importance values are words rather than numbers, notes that every block names its source, and explicitly warns that O*NET data cannot be combined with the impact index. It does not disclose output size or formatting, but the behavioral caveats are unusually specific and useful.

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 dense and long, but it is front-loaded with the core question 'Where an occupation or a degree sits' and every clause adds a distinct piece of information. It would be more digestible as bullets, but for a tool with this much output variety the length is justified.

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 complex tool with no output schema and no annotations, the description covers a remarkable amount: target entities, data sources, output sections, source attribution, fit quality, and a critical caveat. The main missing context is parameter-level behavior, especially locale, which keeps it from being fully complete.

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 0%, so the description must compensate for the undocumented slug and locale parameters. It implicitly suggests slug identifies an occupation or degree, but it never explains what values slug accepts, what locale means, how it affects results, or what the default is. This is a meaningful gap for call construction.

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 states a specific resource (occupation or degree) and the exact data returned: classification codes with fit quality, top O*NET skills, related occupations, degree pathways, task alignments, and verification rules. It clearly differentiates from siblings like get_occupation and get_major by focusing on ontology/classification placement rather than a single profile.

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 when to use the tool: whenever an agent needs classification, skill, task, or rule context for an occupation or degree. It does not explicitly name alternatives or explain when a sibling like query_ontology or get_occupation would be preferred, though it does give one clear warning: never combine it with the impact index.

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