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

Annotations only provide readOnlyHint/idempotentHint/destructiveHint (all false). The description adds substantial behavioral context: it does not void the envelope, preserves collected signatures, returns 409 for already-signed recipients, sends a fresh invite when enabled, and updates future remind calls. It also specifies the auth header. This far exceeds annotation coverage.

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 multi-sentence but every clause adds value: endpoint wrapper, non-destructive behavior, refusal conditions, invite behavior, future remind implications, and auth requirement. It is front-loaded with the core purpose and avoids redundancy, though it could be slightly tightened.

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 modification tool with conditions and an output schema present, the description covers all essentials: what it does, when it refuses, side effects on invites and reminders, and authentication. The output schema handles return values, and the annotation covers idempotency. No critical information is missing for an agent to call it correctly.

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 0%, so the description must compensate. It does: 'email' is the corrected email, 'recipient_id' must be unsigned, 'document_id' is the envelope. It doesn't specify format constraints, but with only three straightforward parameters, the description provides enough meaning to correctly populate them.

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 opens with a precise action: 'Correct the email of an unsigned recipient on an in-flight envelope.' It names the exact resource (recipient) and context (in-flight envelope), and explicitly contrasts with void_envelope ('does not void') and remind_envelope ('Later remind_envelope calls go to the new address'), distinguishing it from siblings.

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 clearly states when to use the tool (unsigned recipient on an in-flight envelope) and lists refusal conditions (already signed, voided/completed/declined/expired). It does not explicitly name alternative tools, but the contrasts with void and remind provide sufficient routing guidance for an agent.

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