Set cover letter and outstanding answers

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

The description reveals a critical side effect not captured by the annotations: changing content invalidates prior approval because approval is bound to the packet hash. This goes beyond the simple readOnlyHint/destructiveHint flags and provides essential behavioral context.

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?

Two sentences, front-loaded with purpose and a crucial behavioral warning. No redundant phrasing or filler.

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?

The description covers the primary function and the most important consequence (approval invalidation). It does not discuss return values, error conditions, or prerequisites like application state, but given the tool's likely straightforward nature and lack of output schema, it is nearly complete.

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 low (25%), with only 'answers' having a description. The description adds meaning for 'coverLetter' and 'answers' but leaves 'notes' unexplained and gives no additional context for 'applicationId'. Since the description partially compensates for the schema gap, a mid-range score is appropriate.

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 uses a specific verb ('Records') and identifies the exact resource (cover letter and outstanding answers). It distinguishes the tool from siblings like prepare_application and approve_application by clarifying that this fills gaps the policy engine doesn't handle.

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 when to use the tool: after preparation, to fill questions the policy engine won't answer. It also warns that changing content invalidates prior approvals, which serves as a caution against inappropriate use. However, it does not explicitly name alternative tools or state when not to use it.

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