Get permitted sender choices

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

Annotations already establish read-only, idempotent, non-destructive and open-world behavior, so the description is not carrying the safety burden. It still adds genuine context beyond the annotations: the result is a policy intersection, subdomains need separate authorisation, and the permissions are re-validated at send time, which tells the agent the result is advisory rather than a guarantee.

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 sentences, none obviously wasteful, but the opening sentence is a dense chain of policy jargon that front-loads mechanics instead of the tool's outcome. Leading with what the tool returns would make the text far easier to act on.

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?

An output schema exists, so return values need not be spelled out, and the description covers the policy-intersection logic, the subdomain caveat and the re-check at send time. What is missing is a plain statement of what a 'choice' actually is (address? identity? provider account?) and whether results are filtered by the delivery group or merely annotated by it.

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 all three parameters (mailbox_id, If-None-Match, delivery_group_id) are already documented in the schema. The description adds only a light gloss by referring to 'selected delivery groups', which corresponds to delivery_group_id, but says nothing about mailbox scoping or the ETag caching parameter. Baseline 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 explains how the result is computed (an intersection of team, inbox and credential policies with provider restrictions and delivery groups) but never states plainly that the tool returns the set of sender addresses/identities that may be used. The verb is implicit and buried in 'Intersects', so an agent must infer the output type from the title rather than the body text.

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?

There is no explicit when-to-use instruction and no reference to an alternative. The clause 'Sending checks these permissions again before submission' hints that this is a pre-send check, but the agent must derive that call ordering itself, and nothing says when this tool should be skipped (e.g., if the caller already knows the allowed sender).

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