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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it discloses the contents of each draft returned (thread info, trigger message, response text, creation/expiration).

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?

Front-loaded with the core purpose, then a compact bulleted field list, then usage triggers. The bullet list is slightly longer than needed but each line earns its place by describing returned content.

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?

With no output schema, the description compensates well by enumerating the returned fields and covering the read-only safety case via annotations. It is essentially complete for a zero-required-param list tool, with only minor gaps around pagination/result ordering.

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 100%, so the read-only parameters (limit, thread_id, in_workspace) are already fully documented in the schema. The description adds no syntax or formatting detail for them, so baseline 3 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?

States a specific verb and resource ('List pending agent drafts awaiting approval') and adds a clarifying scope ('generated by AI agents but not yet sent'). This clearly separates it from sibling list tools like agents_list by specifying the pending-draft domain.

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 explicit trigger phrasing ('Show pending agent drafts', 'What messages are waiting for approval?', 'List drafts to approve') that maps user intent to this tool. It does not name alternatives or exclusions (e.g., that approval itself belongs to agents_approve_draft), so it stops short of full when/when-not guidance.

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