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

Goes well beyond the readOnly/idempotent annotations by enumerating every possible state with its accompanying fields (sentAt, sendAt, approvalUrl, expiresAt), and critically discloses a retention limitation: sends approved via in-app prompt or draft card also read as gone. That caveat prevents a costly misinterpretation of a gone result.

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-loads the safety message and the state enumeration, with no filler sentences. The long inline parenthetical list of states is dense but warranted; a bulleted layout would be marginally easier to scan.

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 full burden of return-value explanation and does so completely: all five states, their associated fields, and the meaning of the ambiguous one. An agent has everything needed to interpret any response 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% and both parameters already state they come from create_draft, so the description's mention of "pendingSendId + approvalCode from create_draft" adds no meaning beyond the schema. Baseline 3 applies since the schema does the work.

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 and resource ("says where one send stands") plus the exact inputs that identify it. It is clearly distinguishable from send_draft (which schedules) and get_send_diagnostics (which is for investigating missing records).

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?

Explicitly frames this as "the safe way to check later" and warns that calling send_draft again can schedule the send, which is the concrete alternative and why to avoid it. It also names get_send_diagnostics as the prerequisite step before making a new draft after a gone result.

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