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

The description adds meaningful behavioral details beyond the annotations: Helvabase rechecks the immutable source and quotation, only selected evidence is stored, it returns a new context revision, and no human approval is granted. While annotations cover read/write/destructive/idempotent hints, the description elaborates on side effects and the rechecking process. It does not contradict the annotations.

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 concise, with each sentence adding distinct value: purpose, constraints, workflow, and approval status. It is front-loaded with the primary action and avoids filler. Slightly longer than necessary but well-structured.

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 tool with 7 parameters, nested objects, and no output schema, the description covers only the core action and workflow. It omits critical details about parameter relationships (e.g., how fragmentIndexes map to quotes, what expectedReadRevision does, what 'destructive' means) and does not specify the return value beyond mentioning a new context revision. The description is inadequate for a reliable invocation without additional lookups.

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 coverage is only 29%, so the description must compensate for explaining the 7 required parameters. It vaguely references 'quotes', 'received page' (pageRevision), 'source', and mentions the returned context revision, but it does not explain the meaning of sourceKey, expectedReadRevision, idempotencyKey semantics, or the structure of pageRevision/contextRevision. The description provides insufficient parameter guidance for an agent to construct correct inputs.

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 clearly states the tool adds exact selected quotations from a received page to the dossier citation catalog, with specific constraints ('consecutive fragments must belong to the same unit'). This distinguishes it from sibling tools like create_evidence or add_evidence_version by focusing on quote selection.

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 provides workflow context (read the new context revision, then submit or refresh analysis before contributions/review) and warns against submitting paraphrases, but it does not explicitly say when to use this tool over alternatives, nor when it should not be used. The when-to-use is implied by the workflow but not stated with sufficient clarity for a complex tool landscape.

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