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

Beyond the annotations, the description discloses substantial behavior: contact fields and raw text are stripped from results, the draft is non-persistent, pasted text is sent (minimized) to an external AI parsing provider, quota may be consumed, and the review handoff only fires when core facts are ready. It also states safety constraints (no patient data, credentials, or secrets) and never contradicts the readOnly/destructive hints.

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 'use this when' trigger and nearly every sentence carries distinct information (trigger, pre-use disclosure, alternative mode, result behavior, quota, constraints). It is dense and clause-heavy though, with several multi-clause sentences that could be split, keeping it just short of ideal.

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 two top-level params, a nested draft object, and an existing output schema, the description covers the modes, privacy handling, external-call/quota caveat, handoff condition, and hard exclusions. Return values need not be explained because an output schema exists; only minor details (e.g., quota specifics) are absent, so it is essentially 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 description coverage is already 100%, so the baseline is 3, but the description adds real meaning: it clarifies that 'job_description' is the pasted-text path that may invoke an external parser and consume quota, while the 'draft' object is the no-parser alternative. This mapping of the two inputs to two distinct modes exceeds the schema's per-field text.

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 first sentence gives a concrete verb pair (parse a job description / structure answers) and a specific output artifact (a privacy-safe, non-persistent anesthesia requisition draft for RxRooster review). The domain ('anesthesia job' vs. the sibling 'anesthesia service' draft) is implied by the resource wording but no sibling is named explicitly, so it falls short of full sibling differentiation.

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?

It states the trigger clearly ('Use this when an employer or recruiter wants to...') and names an alternative path ('Structured draft-only collection is the no-parser alternative'), plus a precondition for the pasted-text mode. It lacks explicit when-not guidance and does not route to any sibling tool, so it stops short of a 5.

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