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

Annotations declare destructiveHint=true and idempotentHint=false; the description goes beyond them by disclosing irreversibility ('no tool to re-subscribe... only undone in the dashboard'), that nothing is sent to the customer, and the HTTP endpoint. This is exactly the extra context an agent needs before an irreversible write.

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-loaded 'WRITE:' marker, then scope, use case, irreversibility warning, side-effect note, and endpoint – every sentence earns its place with no 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 one-parameter irreversible write with no output schema, the description covers purpose, trigger condition, reversibility, and side effects. Nothing an agent needs to call it safely is missing.

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 coverage is 100% for the single email parameter, and the description only restates 'one e-mail address' without adding format or normalization rules. Baseline 3 applies since the schema already fully documents the 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 + resource + scope: 'stops REVIEWS.io sending review invitation e-mails to one e-mail address.' The 'WRITE:' prefix and the endpoint make it immediately distinguishable from read-oriented siblings like reviewsio_list_unsubscribed_users.

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?

'Use it for a customer who asked not to be contacted' gives clear situational context. It doesn't name a sibling alternative (e.g. list_unsubscribed_users to check first), but the no-re-subscribe caveat effectively steers usage.

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