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

With no annotations, the description carries the full transparency burden. It does this well by disclosing offline behavior, fail-closed semantics, default pubkey behavior, the exact allow condition, and the need to poll status for revocation. It stops short of describing failure modes, error responses, or behavior for malformed tokens, but the core decision logic is transparent.

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 carrying distinct value: the mode and posture of the check, the precise allow condition, and the follow-up action. The description is front-loaded with the most important qualifiers ('Offline, FAIL-CLOSED') and contains no filler.

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 two-parameter offline verification tool, the description gives an agent nearly everything needed to invoke it correctly: required input, optional override with default, result semantics, and a follow-up safety step. The main gap is the lack of an output schema or explicit description of the response shape beyond 'allow=true', and edge-case behavior for invalid signatures is only implicit in 'FAIL-CLOSED'.

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 only 50%, so the description meaningfully compensates by explaining that the check is 'against a pinned pubkey (defaults to this server's key)' — this gives real semantic content to pubkey_hex and clarifies it is optional. The lease parameter is already documented as 'A full lease token from vigil_grant_lease' in the schema, and the description reinforces its role.

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 names a specific action ('check of a lease token'), a clear resource, and sharp constraints ('Offline, FAIL-CLOSED', 'allow=true only if the signature verifies and the lease has not expired'). It also sets itself apart from status-style endpoints by noting the gateway should poll status for revocation, making the verification tool's niche clear.

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 clearly conveys when to use this tool: for offline, fail-closed lease checks that never rely on network state. It also gives a usage boundary by stating that revocation must be confirmed by polling status. However, it does not explicitly name alternative sibling tools such as vigil_lease_status or specify when not to use this tool beyond the revocation caveat.

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