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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint:false, and openWorldHint:false, so the description earns credit for adding details the annotations cannot express: the required client-owner role, the sms:write scope, and the installation precondition that Kai be confirmed as the review tool. "It sends nothing and saves nothing" is consistent with the annotations and reinforces the safety profile rather than contradicting it. Rate limits and failure modes are not mentioned.

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: what is shown, what is required, and what it does not do. That ordering puts the core operation first and the safety guarantee last. It is tight with no filler, though the opening sentence is dense enough that the fingerprint clause feels buried inside it.

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 read-only preview whose output schema and annotations are supplied, the description covers operation, prerequisites, and non-side-effects, which is what an agent needs to call it safely. The residual gaps are the purpose of campaignId and the accepted constant, which are left entirely to the schema and are not explained anywhere in the description.

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 67%, so the baseline is 3, and the description does add useful meaning by explaining that the fingerprint is what enables approval and that the payload concerns recipients and sender number. It says nothing about the meaning of the untouched parameters (campaignId, the accepted const, and the concurrency role of expectedRevision), so it does not fully offset the coverage gap.

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 uses a concrete verb and lists the exact resources returned: review-request text, sender number, and recipients, scoped to customers with a completed service. That is enough to tell it apart from a launch or prepare step without opening the schema. It stops short of 5 because it never names the sibling it contrasts with, which the description implicitly invokes when it notes that it sends nothing.

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?

Guidance is implied rather than stated: the mention of "a fingerprint for approval" signals this is the step preceding approval, and the prerequisites (client owner, sms:write scope, SMS review installation with Kai as the review tool) gate when it can be called. There is no explicit when-to-use or when-not-to-use statement and no named alternative, so the agent must infer the workflow position from the wording.

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