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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds traits beyond them: the capability is revocable and time-bounded to at most one hour. It does not explain what happens at expiry, whether revocation invalidates in-flight calls, or how much authority is consumed.

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 with zero filler. The core nature of the tool and its central constraint (one-hour lifetime) are front-loaded, followed by scoping then retry semantics in descending order of importance.

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 six-parameter, security-sensitive tool with nested constraint objects and no output schema, the description covers identity, lifetime, and idempotency well and hints that a token is returned. It omits any mention of the uses cap, the constraints map, or output shape, though the schema documents these fully.

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%, so every parameter already carries field-level documentation including ranges, defaults, and the constraints map semantics. The description paraphrases scope values and op_key retry behavior without adding syntax or format detail beyond the schema. Baseline 3 is appropriate when structured data does the heavy lifting.

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 (Create) and resource (capability), and immediately characterizes it: revocable, carrying part of the caller's authority, bounded to one hour. This distinguishes it cleanly from the sibling revoke_capability and from create_credential, which an agent can separate without opening either schema.

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 scoping options (public reads, one object, your identity, a network session) and retry guidance with op_key, which is implied usage guidance. However, it never states when to prefer this over create_credential, when not to use it, or any prerequisite authority the caller must hold. The routing decision is left to inference.

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