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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, yet the description adds substantive context beyond them: it charges nothing, contacts no attorney, creates no engagement, and document text is never sent (input is facts only). It also clarifies the output is an assessment/offer and not a legal opinion that only the user can accept. This is meaningful disclosure an annotation can't convey.

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?

Well structured and front-loaded: purpose first, then labeled 'Call it when' / 'Don't call it for' blocks, then read-only and return notes. It is on the long side — the six-item trigger list has some overlap (payments, personal data, and finalization are closely related) — but each section is scannable and earns most of its space.

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?

No output schema exists, and the description fully compensates by describing the return (an assessment of timeliness, which documents exist, what's missing, scope fit) plus a conditional offer, and it clarifies the acceptance model relative to accept_human_function_offer. Nothing an agent needs to call it correctly is missing.

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 all 13 parameters (enums, required fields, lengths) are documented in the schema itself. The description adds only general framing ('inputs are facts about the product and documents; document text is never sent') rather than parameter-level meaning, so the baseline 3 is appropriate.

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: it checks whether a situation fits HumanFn's SaaS Launch Legal Review and returns the exact offer. It draws sharp scope boundaries (only a SaaS's own ToS/Privacy Policy, attorney review of final docs), letting an agent tell it apart from adjacent legal/counsel questions without opening the schema.

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?

Provides an explicit 'Call it when:' list of six concrete triggers (final/near-final ToS or Privacy Policy generated or edited, pre-launch, user asking if AI legal pages are safe, payments starting, personal data collected, otherwise shipping on a generic caveat) and a matching 'Don't call it for:' exclusion list. Nothing about when to invoke vs. skip is left to inference.

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