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

Beyond the readOnly/destructive annotations, it discloses the core mechanic: this only materializes an approval card, 'Sends nothing', and only a human click queues the wave ('no UI means no sending'). That is exactly the consequence-and-control context an agent needs for a high-stakes gate; the 'creates a card' side effect is the only mild tension with readOnlyHint, but the description frames it as non-sending, not as a data mutation.

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?

Short, front-loaded sentences with the prohibition placed prominently; nothing superfluous. 'Sends nothing' and 'no UI means no sending' overlap slightly, but the deliberate repetition serves a safety-critical point 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?

For a safety-gate tool with no output schema it covers the critical workflow: read first, request approval, human click sends, never self-confirm. What is missing is what the call returns (card identifier, status, revision-mismatch failure), which the agent would need to act on the result.

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 0%, so the description must carry parameter meaning, and it largely does not: neither waveId nor expectedRevision is explained, and the 64-hex-hash pattern for expectedRevision (a revision/conflict guard) is never described. 'The exact quoted wave' and 'read get_letter_wave first' only indirectly hint at where the revision comes from.

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 names a specific verb and artifact: 'Request one human approval card' for a quoted wave, and enumerates the scope it covers (recipients, texts, print specification, count, total). It explicitly separates itself from confirm_letter_wave_send, so an agent can tell the two apart without opening either schema.

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 an explicit precondition ('Read get_letter_wave first') and explicit prohibitions ('Never infer approval from chat', 'never call confirm_letter_wave_send from the model'). The when-not and the alternative are both stated, leaving little to inference.

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