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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description does not need to restate safety properties. It adds useful behavioral context beyond annotations by warning that a dossier approval should not be treated as approval of reusable knowledge. This is an extra domain rule that helps the agent behave correctly, though the description still does not say anything about pagination, return shape, or what a 'revision' contains in practice.

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 description is two sentences with no fluff. The first sentence leads with the action and the exact when-to-use context; the second sentence is a useful caution. Both sentences carry meaningful weight, and the structure is appropriately front-loaded.

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 simple read tool with two required parameters and full annotation coverage, the description supplies enough context to know why the tool exists and approximately when to call it. It is incomplete in two material ways: answerId semantics are missing, and the description never states what the tool returns (e.g., whether it includes full answer text, timestamps, authorship, or the archival revision). Given no output schema, these omissions leave room for agent error.

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?

With 50% schema description coverage, answerId is entirely undocumented in the schema, and the description also fails to clarify its meaning or relationship to projectId. The phrase 'questionnaire answer' gives a weak clue that answerId identifies an answer, but projectId is only explained inside the schema and the description does not help map the two parameters. For low coverage, the description should compensate, and it does not.

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 description states a specific action and object: 'Read the exact questionnaire answer and its revision.' It also ties the reading to the downstream goal of proposing reusable knowledge or adapting a suggestion, which distinguishes its purpose from many sibling read tools. It is not a full 5 because the tool name 'library_source' is not explicitly reconciled with the object being read, and the actual return value is not made explicit.

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 clear timing guidance: use this before proposing reusable knowledge or adapting a suggestion. It also gives a domain caveat with 'A dossier approval never approves reusable knowledge,' which prevents a common misuse. It does not explicitly name alternative tools or provide a full when-not-to-use list, so it stops short of 5.

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