send_email

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

Annotations already declare this as a non-read, non-idempotent, non-destructive write. The description adds a genuine behavioral nuance ('approval/alert bypass quiet hours') and names the channel (Gmail), but says nothing about immediacy, confirmation, or reversibility.

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?

Two short sentences with the core action front-loaded and the kind/quiet-hours details following. No filler, though the phrasing is slightly telegraphic.

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-param email tool with no output schema, the description covers recipient, channel, kind taxonomy, and a delivery nuance. It is adequate but leaves open whether the send is immediate/unrecoverable and what the required subject/body constraints are.

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 0%, so the description carries the burden. It supplies the enum values for kind (report|approval|alert|retro), compensating for one parameter, but subject and markdown_body receive no added semantics in either the schema or the description.

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 (Email) and a clear resource/recipient (the owner, via Gmail), so the agent immediately knows what the tool does. It is the only email-capable sibling, so differentiation is implicit rather than stated.

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?

The kind list (report|approval|alert|retro) gives some guidance on intent, but there is no explicit when-to-use vs when-not-to-use guidance. The tool is unique among siblings, so usage is inferable but not spelled out.

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