analyze_work_authorization

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses that the result is a confidence-scored keyword heuristic (not legal advice), that a supporting quote is returned, that no input is stored, and that the agent must instruct the user to verify with the employer. Those epistemic and retention caveats are exactly the kind of context annotations cannot carry.

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 core action is front-loaded in the first line, followed by the label set, the disclaimer, and the input constraint in four tight blocks with no filler. Every sentence adds either scope, output shape, or a caveat the agent must relay.

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 an output schema present, the description doesn't need to explain return values, and the listed labels plus confidence/quote note are sufficient orientation. The remaining gap is edge-case behavior — what happens if both job_id and text are supplied, or if neither is, and how much text fits within the 30k limit.

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 per-parameter meanings are already documented, but the description adds a rule the schema does not enforce: exactly one of job_id or text, with the title parameter valid only alongside pasted text. That mutual-exclusivity constraint is genuine added meaning, though the failure mode on violation is not stated.

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?

"Classify a posting's visa-sponsorship / citizenship / clearance stance" is a specific verb plus resource, and the enumerated label set (sponsorship_offered, no_sponsorship, citizen_only, clearance_required, unclear) makes the output scope unambiguous. It is clearly distinct from the retrieval siblings (search_jobs, get_job_details) because it produces a classification, not a record.

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 the key selection rule: "Provide exactly one of job_id or text," and the schema note ties job_id to ids from search_jobs, so the agent knows the two entry paths. It stops short of explicit exclusions or telling the agent to call get_job_details first when it lacks posting text.

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