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

Goes well beyond the annotations: the key is returned only once and must be stored, revocation lives in Settings → API, and the operation has an auth prerequisite (email confirmed) and required scope/role. Annotations cover the safety profile, and the description adds lifecycle and irreversibility context.

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?

A single tight paragraph, front-loaded with what the tool does, then return format, prerequisites, and permissions. Every sentence carries information an agent needs.

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?

With no output schema, the description explicitly gives the return shape ({ apiKey, id, name, scopes, usage }) plus lifecycle, auth, and permission constraints. Nothing needed to invoke it correctly 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% with descriptions on both params, so the schema already carries the parameter meaning; baseline 3 applies. The description's 'Requires scope locations:write (Admin role)' concerns the caller's token, not the scopes argument, so it adds little param-specific detail.

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 ('Create a long-lived API key') plus the concrete key format (sd_live_…) and its audience (scripts/clients that can't refresh OAuth). No sibling tool manages keys, so it is trivially distinguishable.

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?

Gives explicit when-to-use ('scripts and clients that can't refresh OAuth tokens') and prerequisites ('Needs the owner's email confirmed first' and 'Requires scope locations:write (Admin role)'). It even closes off a plausible alternative path by noting keys can't be listed or revoked over MCP.

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