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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely new behavior: Regent evaluates the policy, injects the credential, and the key never reaches the agent. It still omits what happens on a policy denial or how the call is authenticated for the user_token path.

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 front-loaded sentences with no filler: the target and method constraint come first, then credential handling, then the safety guarantee. 'Nothing is changed and no money moves' partly restates the readOnly annotation, a minor redundancy.

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?

Covers the safety profile, credential flow, and method limits for a 5-parameter tool with a nested facts object and no output schema (so return values need not be explained). Gaps are minor: no guidance on required 'path' format beyond the schema, or on failure when the policy denies the call.

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 80%, so the schema already documents path, facts, intent, and user_token; the description adds only indirect meaning ('policy' hints at facts, and intent's audit role is implied but not restated). Baseline 3 is appropriate since the schema carries the parameter semantics.

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 (read) and specific resource (https://api.agentmail.to), and pins the allowed methods to GET/HEAD/OPTIONS, which the _read naming pairs with the plain `agentmail` sibling as the write path. It does not explicitly name that sibling, so the 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?

Clear context for use: read-only access routed through Regent, method-limited to GET/HEAD/OPTIONS, with 'Nothing is changed and no money moves' confirming the scope. There is no explicit when-not rule or named alternative for cases needing a write, so it stops short of a 5.

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