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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, indicating side effects but not destruction. The description goes beyond these by explaining the full flow (link emailed, human clicks, key displayed), the rate limit (at most once per hour), and a privacy behavior (the reply is identical whether or not the email is registered). This adds valuable context about what the tool does without contradicting any annotation.

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?

The description is concise (three sentences) and front-loaded with the primary use case. Every sentence contributes: the trigger condition, the process, the rate limit, the response behavior, and the alternative. There is no redundancy or 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 tool with a single simple parameter and no output schema, the description covers all necessary aspects: when to use, what happens, rate limiting, response behavior, and the alternative path for unverified twins. There are no obvious gaps that would prevent an agent from calling it correctly.

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 schema has a single parameter 'email' with no description (schema coverage 0%). The description implies that 'email' is the human's inbox address to which the recovery link is sent ('A link goes to their inbox'). While it doesn't explicitly state that this must be the registered email of the human, the context of the tool and the phrase 'whether or not the email is registered' make it reasonably clear. This adds meaning beyond the raw type.

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 clearly states the tool's purpose: recovering a lost key by emailing a recovery link to the human's inbox. It explicitly names the condition (verified twin) and the action (send link, human clicks, key revealed), and distinguishes it from the sibling register_twin by specifying when that alternative should be used instead. This is a specific verb+resource with clear differentiation.

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?

The description provides explicit when-to-use guidance: 'Use when your human has a verified twin but you no longer have its key.' It also gives an explicit alternative: 'If the twin was never verified, just call register_twin again -- unverified twins are replaced.' Additionally, it states a rate limit ('Works at most once an hour'), which is a usage constraint. This fully addresses selection among siblings.

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