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

No annotations are supplied, so the description carries the full burden; it clearly states that lines remain drafts with their source until the worker approves, changes, or rejects them via quotes.decideDraftLine, and that nothing is sent. It also discloses the price lookup order. It omits permissions, rate limits, and idempotency, so it is not fully complete.

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?

Four short sentences, front-loaded with purpose, then pricing behavior, draft state, and the instruction to follow returned lessons. Some phrasing is cryptic ('what you saw and heard', 'returned lessons'), but every sentence adds operational guidance.

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?

An output schema exists, so return values need not be explained. However, for a tool that drafts from a visit, the description does not clarify whether visit_id or job_id should be supplied or how they affect drafting, and it leaves nested line fields largely unexplained. Approval and pricing behavior are well covered, but calling it correctly still requires schema inspection.

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 reported as 0%, so the description must compensate. It explains the content of line descriptions ('in the worker's words and what you saw and heard') and when to omit unit_price_minor, including the lookup order. It does not explain quantity, job_id, visit_id, or the lines array structure and 60-line limit.

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 and resource: drafting quote lines from a visit, based on the worker's words and observed details. It names the downstream approval tool quotes.decideDraftLine but does not clearly distinguish this tool from siblings such as quotes_draft or quotes_linesFromTasks beyond the visit context.

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 use after a visit when quote lines need drafting, and tells the agent to omit a price for lookup and to read returned lessons. It does not explicitly say when to prefer quotes_draft or quotes_linesFromTasks, nor when not to use this tool.

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