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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the description's job is to add context, which it does: it clarifies this is a price-read-only operation that never sends, explains the confirmPriceRead flag semantics, and documents the revision-echo iteration protocol. It does not detail what happens on revision mismatch or how the total is formatted, keeping it from a 5.

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?

Dense and front-loaded: the never-sends guarantee and the confirmPriceRead scope come first, followed by prerequisites and iteration rules. The final sentence about not claiming a campaign was sent is slightly editorial but reinforces a real misuse risk.

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 3-parameter mutation-flagged tool with no output schema, the description covers the safety contract (never sends), the confirmation flag, tenant policy preconditions, the repeat-until-quoted loop, and the handoff to request_letter_wave_send. Only the failure modes (stale revision, blocked status) lack detail.

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. It explains expectedRevision ('the current expectedRevision') and confirmPriceRead ('confirms these price reads only') and implies waveId through 'one batch of the stored wave' and 'Repeat ... using the returned revision', but it never explains why expectedRevision must be a 64-hex string or what happens when it is stale.

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 and resource: explicitly approved provider price reads for one batch of the stored wave. It clearly distinguishes itself from sending via the explicit 'never sends' clause, though the sibling relationship to get_letter_wave and prepare_letter_wave is only implied.

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 explicit when-to-use conditions (requires expectedRevision and confirmed tenant policy), an iteration rule ('Repeat while status=quoting using the returned revision'), and names the alternative path (request_letter_wave_send displays the approval card). It also states a prohibition: a blocked wave is not sendable.

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