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

Annotations already mark the operation as destructive and idempotent; the description adds value by explaining the replay-protection behavior and the reclaim path for never-delivered drafts. This is consistent with the annotations and clarifies what 'send' entails without contradicting the schema.

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?

A single two-clause sentence states the core action and the two supported modes with no filler. The main action is front-loaded, and each clause contributes meaning.

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 explains the key behavioral choices (send vs. reclaim) and the replay-protection safeguard, which is enough to select the tool. However, it does not explain the request_id parameter, possible error/return conditions, or any precondition such as a configured sender, and there is no output schema to fill those gaps.

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 0% schema description coverage, the description carries most of the semantic load. 'Replay protection' and 'reclaim a never-delivered draft' clarify the likely purposes of idempotency_key and reclaim_not_delivered, but the description never mentions request_id and leaves the id/draft relationship implicit.

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 'Send a pending candidate email draft,' giving a specific verb and resource, and outlines a distinct reclaim mode. This clearly separates it from sibling draft tools like yardstick_email_drafts_read or _discard, which serve different purposes.

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?

It specifies when to use the tool: for pending drafts in the normal path, or for never-delivered drafts via reclaim. It does not explicitly name sibling alternatives or state when not to use it, so it falls short of a 5.

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