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

Annotations already declare write, idempotent, destructive, and open-world behavior. The description adds useful partial-update semantics ('Only the fields you pass change'), confirms no sending occurs, and identifies the PATCH endpoint, but it does not elaborate on destructive implications or authorization requirements.

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?

It is short and front-loaded with 'WRITE', then immediately states the editable fields and the key behavioral constraints. Every sentence adds signal without repetition.

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 13-parameter write tool with rich annotations and mostly described schema fields, the description is nearly complete: it explains partial updates, non-sending behavior, and the endpoint. It could say more about destructive risk or permissions, but those are partly covered by annotations.

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?

The schema has 77% description coverage across 13 parameters, so baseline is near 3. The description groups editable fields and notes partial-update behavior, but it does not add detail beyond the schema for most parameters, such as reply_to, from_name, or the content variants.

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 states a specific verb (change) and resource (a saved message) and names the editable fields (name, subject, sender, folder, body). It also clarifies that it does not send anything and gives the PATCH endpoint, making it easy to distinguish from create/send 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?

It clearly establishes the editing context with 'Only the fields you pass change' and 'It does not send anything.' However, it does not explicitly name when to use this versus create_message or get_message, nor does it list prerequisites or exclusions.

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