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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description goes far beyond that: it discloses an internal validation step, an external gate dependency, the failure modes that block sending, the re-invocation flow after wait, the requirement of a connected Agentmail inbox, and seat/pricing applicability. Rich behavioral coverage the annotations do not provide.

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 'Write Gate' and the core purpose, and each sentence carries required workflow detail. It is dense with gate jargon and slightly run-on, and the 'does not send' conditions repeat across two sentences, but nothing is gratuitous.

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 carries the return-behavior burden and does so: it explains what each decision (go/wait/stop) means for the caller and the follow-up needed. For a gated write tool with five params, an agent has everything required to call it correctly.

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 each parameter is already documented in the schema (including approval_id's origin from a previous wait). The description adds contextual flow for approval_id but no new syntax or format beyond the schema. 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+resource (send email) with a clear qualifier (only after human approval via Action Gate). It names the sibling tools it orchestrates (check_action, get_approval) so an agent can distinguish it from those. No ambiguity about what the tool does.

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 and when-not: it sends only when decision is go; on wait it directs the agent to poll get_approval then re-call with approval_id; it enumerates the failure conditions (unpaid, missing DATABASE_URL, stop, timeout, inbox not connected) that suppress sending. Alternatives and sequencing are fully spelled out.

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