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

Annotations declare destructiveHint=true and idempotentHint=false, and the description meaningfully extends that with the gating/escalation model, the retry-with-same-idempotency_key execution rule, and the assurance that the credential never reaches the agent. It stops short of describing what a successful response contains or how destructive operations behave against existing remote state.

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 tight sentences, front-loaded with the action and target, followed by the operational caveats. No filler; the escalation and idempotency details are load-bearing rather than padding.

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 still covers the key outcome an agent needs (ESCALATION_REQUIRED parking and how to execute after approval). For a generic proxy over arbitrary paths, the behavioral picture is largely complete, though response shape and failure modes beyond escalation are unstated.

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 86%, so the schema already explains path, body, facts, intent, user_token, and idempotency_key. The description reinforces idempotency_key's retry role but adds no new meaning for the remaining parameters, so the baseline of 3 applies.

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 set (create, change, pay) against a named resource (https://api.agentmail.to via Regent) and enumerates the HTTP methods involved. The '· write' title and method list make it distinguishable from the agentmail_read sibling, though the description never names that alternative explicitly.

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 gives real usage context: calls are gated under a spend limit, unapproved payments are parked as ESCALATION_REQUIRED, and retries must reuse the same idempotency_key. However, it never says when to choose this tool over siblings like pay, stripe_demo, or agentmail_read, so routing is left to inference.

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