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

Annotations already declare destructiveHint=true and idempotentHint=true, so the agent knows this is a destructive operation with idempotent behavior. The description adds critical context: it requires human authorization, the content becomes frozen, repeated calls recover the same submission without sending another copy, and earlier retrieval does not lock content against edits. This goes beyond annotations, providing necessary operational details.

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?

Three concise sentences, each earning its place. Front-loaded with the core action and authorization requirement, then idempotency behavior, then a clarification about retrieval. No waste.

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?

Complete for a send tool with idempotent and destructive annotations. The description covers authorization, idempotency, and a non-obvious caveat about retrieval not locking edits. Output schema exists, so return values needn't be explained. Nothing an agent needs to call it correctly is missing.

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 50%, so the schema documents draft_id and idempotency_key. The description doesn't add parameter-specific details beyond what's in the schema (e.g., format, constraints). Baseline 3 is appropriate when schema does the heavy lifting.

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?

States a specific verb+resource: sending a draft's saved content. It distinguishes from send_message by emphasizing 'draft's current saved content' and from update_draft by referring to a frozen submission. However, it doesn't explicitly name the sibling tools it should be compared with (send_message, get_draft).

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?

Provides clear context: use only when authorized by the human. It implies when not to use it (earlier retrieval does not lock content against edits), but doesn't explicitly name alternatives like send_message. The guidance is clear but lacks explicit alternatives.

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