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

The description explicitly characterises the operation as a write ("do not retry the write, reconcile it") and describes spending/consuming a lease, which mutates ledger state, while annotations declare readOnlyHint=true. This directly contradicts the structured safety metadata, so the description cannot be trusted to describe the failure modes the agent needs.

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?

Four short sentences, front-loaded with the core action and atomicity guarantee, then return shape, retry protocol, and cost. No filler; every sentence carries actionable information.

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 mutation tool with six params and an output schema present, the description covers atomicity, blocked conditions, return shape, retry/reconcile protocol and pricing. The main gap is that it does not resolve the read-only annotation conflict, leaving the agent unsure whether this is a side-effect-free call.

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 all six parameters are already documented, including use_nonce's replay-key semantics. The description mostly restates this ("SAME use_nonce") and adds only the cost signal, which is not parameter semantics.

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 and resource with exact scope: "Spend exactly one use of a lease, atomically." The atomicity and single-use framing clearly separates it from vc_lease_issue, vc_lease_revoke and vc_lease_status without needing their schemas.

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-call-again guidance ("If a previous attempt timed out, call this again with the SAME use_nonce") and an explicit when-not ("do not retry the write, reconcile it"). It does not, however, name which sibling to use for checking lease state or when to prefer vc_lease_status over consuming.

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