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

With no annotations supplied, the description carries the full burden. It usefully discloses that changes and rejections are persisted with their reason and feed back into the next draft, which is genuine behavioral context. It does not say what the call returns, whether it is idempotent, or what happens if the same line is decided twice — meaningful gaps for a mutation tool.

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?

Three short sentences with the action first, the constraint second, and the downstream consequence last. No filler, and each sentence carries information an agent cannot get from the schema.

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 six-parameter mutation tool with no annotations, the description covers the action, the per-line granularity, the source of truth for the answer, and the persistence of reasons; the output schema covers return shape. Remaining gaps are edge-case semantics (repeat decisions, error conditions) rather than core calling information.

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 only 17%, so the prose must compensate, and it largely does: it maps approve to optional word/quantity/price changes (description, quantity, unit_price_minor) and ties reason to rejections and modifications. It still leaves ambiguity on whether reason is required when rejecting and on the minor-unit convention for unit_price_minor.

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: record the worker's decision on one drafted quote line, with the two possible outcomes (approve/reject) spelled out. An agent can distinguish this from quotes_draft or quotes_finishDraft by the 'one drafted line' scope, though neither sibling is named explicitly.

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?

Gives a real usage constraint — 'Call only with the worker's own answer, one line at a time' — which implies this runs after a draft exists and must be repeated per line. It stops short of naming alternatives (quotes_draft to produce lines, quotes_finishDraft when all lines are decided), so the workflow boundary is inferred rather than stated.

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