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

Annotations only indicate openWorld=false, idempotent=false, destructive=false, leaving behavioral disclosure to the description. It openly warns that fullKey is returned exactly once and cannot be recovered, notes that the new key never outlives the calling key, and states authorization scope plus revocation path. This is exactly the kind of critical behavioral context the agent needs.

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 compact yet information-dense: core action, recovery use case, one-time retrieval warning, authorization scope, and revocation location all fit into four purposeful sentences. Warnings are front-loaded after the main verb, making the critical 'only once' instruction immediately visible.

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 three-parameter tool with no output schemaebur, the description covers the full behavioral picture: what the tool does, when to use it, critical irreversibility, scope limitations, lifecycle relative to the calling key, and how to revoke. No essential contextual gap remains for an agent to select and invoke 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?

Schema description coverage is 100%, with id, name, and readOnly each already well documented, including defaults and behavior. The description does not add parameter-level details beyond what the schema provides, so it meets the baseline without compensating for any schema gaps.

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?

Description opens with a specific action, 'Mints a new API key bound to a workspace', and clearly differentiates from siblings like create_workspace by emphasizing it is tied to an already-owned workspace and specifically designed for key recovery. The relation to sub-workspaces and main workspace keys adds precise scope.

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 states the concrete scenario: recovering a lost workspace key without UI intervention wheelchair. It may not explicitly list alternatives, but the scenario strongly implies this is the specialized tool for that case, while other create_* siblings serve different purposes. Clear context, though no explicit exclusions.

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