Approve estimate

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 marginal job is the side-effect profile — and it delivers the key fact that no email is dispatched. It still omits what happens on failure (invalid ID, non-draft state) and what the mutated estimate looks like afterward.

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?

Two short sentences, front-loaded with the action and immediately followed by the most likely point of confusion (that it does not send an email). No filler.

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 one-parameter mutation with annotations covering safety and idempotency and no output schema, the description supplies everything an agent needs to pick and call it correctly: the action, the state prerequisite, and the absence of an email side effect.

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?

The single estimateId parameter is 100% documented in the schema, so the description owes nothing extra there and provides nothing extra. Baseline 3 applies for a high-coverage schema with one parameter.

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 ('Approve a draft estimate') plus the resulting state transition ('so it can be sent'). The clause 'Does not email it' separates it from the sibling send tools (wave_send_estimate, wave_send_estimate_acceptance_email) without naming them.

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?

Implicitly tells the agent to use this when a draft needs to become sendable, and rules out emailing as its effect. It does not name the alternative tool to call for sending, nor state the precondition explicitly as a requirement (what happens if the estimate isn't a draft).

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