create_scoped_key

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

Beyond the annotations (which show this is a non-read, non-destructive, non-idempotent mutation), the description adds critical behavior: the plaintext key is returned exactly once and cannot be retrieved later. This is essential for the agent to handle the response correctly. No contradiction with annotations.

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 three concise sentences with no wasted words. Each sentence adds value: purpose, usage context, and critical behavioral warning. Front-loaded with the key fact about the prefix and scoping.

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?

The description covers all necessary context: what the tool does, when to use it, prerequisites, behavior of the return value (plaintext key once), and that it cannot be retrieved later. With no output schema, the description adequately explains the return behavior. The sibling tools provide additional context for lifecycle management.

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?

Both parameters (label and agent_id) are fully documented in the input schema with descriptions and constraints. The description does not add any additional semantic meaning beyond what the schema provides. Schema coverage is 100%, so baseline 3 is appropriate.

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 creates an agent-scoped API key with a specific prefix (chr_ak_*). It highlights the key can only act on behalf of a single agent, which distinguishes it from other key-related tools like list_scoped_keys and revoke_scoped_key.

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 explicitly tells when to use this tool (self-provision or rotate per-agent credentials) and includes a crucial prerequisite (requires an org-level API key). It lacks explicit when-not-to-use guidance, but the sibling tools cover alternate operations like revocation and listing.

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