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

Beyond the annotations, it discloses the single most important behavioral trait: the key is "shown once, keep it", meaning the value is unrecoverable after the response. It also adds rate-limit consequences and the human-confirmation dependency for contact_email, which the agent would otherwise have to discover by failure.

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 short sentences, each carrying distinct information — credential issuance, how to use the key, and the email gate — with the critical "shown once" warning front-loaded. Nothing is 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 two-parameter mutation tool with no output schema, it covers issuance, usage, and the email prerequisite well. It does not say what the response body contains (field name of the key, agent identifier) or what happens if an agent registers twice, which an agent preparing to parse the result would want.

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%, so both parameters are already documented, and the description largely restates the contact_email condition while adding only that a confirmation link is sent. The name parameter gets no added semantic context beyond the schema's own example.

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?

"Issue an API key for your agent" is a specific verb+resource and immediately separates this tool from the event-reading siblings, which do not issue credentials. It does not explicitly name a sibling or state that this is the onboarding step before the event tools, so it stops short of full 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?

It gives concrete downstream usage ("Send it as Authorization: Bearer <key> on later requests for higher rate limits") and a conditional prerequisite ("Give a contact_email to be able to create events"), which effectively tells the agent when and how this tool's output is used. It lacks explicit when-not-to-use guidance, e.g. whether to skip this if a key already exists.

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