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

Annotations already cover the read-only/idempotent/safe profile, and the description adds genuinely new behavioral context: the auth mechanics (token via argument or Authorization header), that 'any live' token works, and that v2 passes don't expire by default. It does not disclose rate limits or response format, so not a 5.

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 sentences, each earning its place, with the read-only framing and resource front-loaded before the auth detail and the usage line. The em-dash enumeration of return fields is dense but not wasteful.

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 compensates by describing what the grant inspection returns and how to authenticate. Complete enough for a zero-required-param read-only tool; only minor gaps (no pagination or response-shape detail) remain.

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 already 100%, so the baseline is 3. The description adds the vs_cap_… token prefix and the 'any live' validity condition along with the alternate header injection path, which is marginal but real added meaning over the schema text.

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 (inspect) and resource (your capability-token grant) and enumerates exactly what it surfaces: scopes in plain words, expiry, remaining daily budgets, recorded account, and audit trail. An agent can distinguish this from siblings like request_capability_token without opening any 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?

Gives a clear when-to-use ('see what you're allowed to do before acting') and a secondary purpose (show your human what happened under the grant). It stops short of naming alternatives such as request_capability_token for when no token exists yet.

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