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

Annotations already declare it as non-read-only, idempotent, and destructive. The description adds behavioral context beyond that: it 'checks selected item completeness and shared current versions', blocks when required documents are missing, and specifies what the reviewer must verify. These details explain the tool's operational effect without contradicting the annotations, which is valuable given that the destructive hint is not otherwise elaborated.

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 three sentences with no filler. It front-loads the primary purpose ('Request final human cross-document review of the exact complete pack') and then adds necessary detail about checks and blocking. Every sentence earns its place, making it efficiently scannable for an agent.

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?

Given the complexity (5 required params, nested objects, no output schema, and low schema coverage), the description is insufficient for an agent to construct correct arguments. It does not explain what planRevision, planConfirmationId, or the structure of documents/selection represent, nor the implications of the destructive annotation. The tool's behavior is partially described but the input requirements remain opaque.

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 20% (only idempotencyKey is described). The description gives vague hints (e.g., 'selected item completeness' relating to selection, 'shared current versions' possibly relating to documents) but does not explain the meaning of planRevision, planConfirmationId, documents, or selection in any detail. For a tool with 5 required nested parameters, the description fails to compensate for the lack of schema documentation.

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 a specific action (requesting a final human cross-document review), the resource (the complete pack), and the precise context (after separate file approvals). It also mentions what the tool checks (selected item completeness and shared current versions) and what the reviewer must verify (identity, prices, dates, signatures, consistency), which distinguishes it from generic review tools like helvabase_request_review.

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 contextual usage guidance: it must be used 'after separate file approvals' and for the 'final' review. It also states a blocking situation ('Missing required documents block'), which is a precondition. However, it does not explicitly name alternative tools or when not to use it, though the context given is sufficient for basic routing.

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