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

With no annotations, the description carries the full burden and provides valuable behavioral context: it is a portable, Ed25519-notarized declaration, and it explicitly states 'Facts, not judgments — attests what was declared, not that the grantor holds the authority.' This non-obvious limitation is critical for an agent to understand. It also discloses price/tier. It could mention more about authentication or side effects, but the disclosed traits go beyond a basic action statement.

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 moderately sized and front-loaded with the primary action. It packs essential facts (format, scope fields, verification pointer, non-judgment caveat, price) into three sentences. The parenthetical price block is a bit cluttered but acceptable. It could be trimmed, but it earns its place overall.

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 13-parameter tool with no output schema and no annotations, the description covers the core purpose, the grant format, key scope fields, the portable nature, the verification path, and the critical epistemic limitation. It is sufficiently complete for an agent to understand when and how to invoke the tool, though it doesn't describe return values (which is acceptable given no output schema).

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 77% (10 of 13 params), so the schema already explains most parameters. The description merely lists some of the fields (allowed_actions, allowed_merchants/domains, spend_max_usdc, principal, consent_ref, expires_at) without adding meaning beyond the schema's own descriptions. There is no extra semantic detail, 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 action ('Mint a signed permission grant') and the resource ('onyx-perm-grant/v0 for an agent'), and differentiates it from the sibling onyx_perm_check by explicitly directing verification to that tool. The verb+resource+scope is specific and unambiguous.

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 gives clear usage context: it mints a grant to be carried on the agent card, and explicitly points to onyx_perm_check for evaluating actions against it. While it doesn't list explicit when-not-to-use scenarios or other alternatives, the named sibling provides sufficient differentiation for an agent to choose correctly.

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