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

With no annotations, the description carries the full burden. It discloses the scope of consent (only acting on a human's behalf with their data) and hints that the failure response teaches the remediation path, but it never states that this is a safe read-only check, nor what the success/failure response actually contains. Behavioral coverage is suggestive rather than complete.

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?

Front-loads the core purpose before the scope caveat and the remediation flow, and each sentence adds distinct value. The inline '[KEEP · internal]' tag and the somewhat lyrical phrasing ('teaches the way') add minor noise but don't obscure the point.

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-param tool with no annotations and no output schema, the description covers the concept, scope, and remediation flow well, but leaves gaps: grantor_pubkey's meaning is only implied and the actual return payload for both authorized and unauthorized outcomes is left vague.

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?

Three required params at 0% schema coverage, so the description must compensate. It clarifies agent_fp ('this agent's key fingerprint') and verb ('a named verb'), but grantor_pubkey is only implied by 'the human issues a grant' and never explicitly defined, leaving one parameter's semantics under-specified.

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+resource: check whether a human has authorized this agent's key fingerprint for a named verb. It also carves out the important boundary that acting as yourself needs no consent, which sharpens the purpose. No sibling tool is named, but the scope is clear enough to distinguish it from the many unrelated siblings.

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 context (the covenant's 'request human authorization before writes') and a clear when-not (speaking as your own key is not proxying, so no consent is needed). It even routes the unauthorized case through the grant flow (GET /consent/signable, sign, POST /consent), providing the alternative path, though no sibling tool is named.

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