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

Annotations declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds real behavioral context beyond that: the mutation must be user-initiated, targets only pending/awaiting-approval emails, and the same file may be reused across emails (implying non-destructive). It stops short of stating failure behavior or whether the attachment is copied vs. linked.

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 short sentences, front-loaded with the action, then the usage guardrail, then the parameter sources. No redundant or filler text.

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 3-parameter mutation tool with 100% schema coverage, no output schema, and safety annotations, the description plus schema plus annotations cover everything needed to call it correctly: when to invoke, what the target must be, and where the id comes from.

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 100%, so the baseline is 3. The description adds genuine meaning for recipient_email ('targets a queued email (pending or awaiting approval)') and reinforces the source of attachment_id (list_attachments), which is new qualifier information beyond the schema text.

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 precise verb (attach), resource (a file from the user's library), and target (a queued outreach email). The scope is tight enough that an agent can immediately distinguish this from detach_from_outreach and the various list/get 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?

Explicit when-to-use ('only attach when the user explicitly asks to attach a specific file to a recipient's email') and an explicit when-not ('never on your own initiative'). It also constrains the target to queued emails (pending or awaiting approval), leaving little to inference.

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