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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description carries the burden. It discloses key behaviors: the tool is free, it refuses (never a silent no-op) when the entry is no longer pending, and it explains the rationale (preventing overwrite of probe verdicts). It also reveals the authorization model (id possession is sole auth). This exceeds what annotations provide and gives the agent a complete picture of side effects and guarantees.

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 compact but information-dense. It front-loads the core action in the first sentence, then adds crucial caveats (authorization, refusal behavior), and ends with an unrelated feedback note. While the feedback note is tangential, it is brief and clearly separated. The structure is logical and not wasteful, though slightly longer than strictly necessary for calling the tool. A 4.

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 simple tool with one parameter and no output schema, the description covers all essentials: purpose, authorization, refusal conditions, and even the rationale. An agent knows exactly when to call it, what to expect (it may refuse), and that it is free. No critical information is missing; the description is fully self-contained for correct invocation.

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 100% for the single parameter 'id', which is described as 'The entry id returned by deadman_register.' The description adds important semantic context: 'possession of the id is the entire authorisation,' clarifying that the id alone is the credential. This goes beyond the schema's simple description, enriching the agent's understanding of how to handle the id securely. Thus a 4 rather than the baseline 3.

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 opens with a clear, specific statement: 'FREE: the live caller closes the loop before the lease expires, so the probe never runs.' This defines the action (close the loop) and the resource (an intent/deadman entry), distinguishing it from siblings like deadman_register (creates) and deadman_read (reads). It also clarifies the scope ('Deliberately NOT wallet-scoped') which differentiates it from other tools in the set.

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 implies when to use this tool: when the live caller wants to confirm before lease expiration. It explicitly notes the authorization model ('possession of the id is the entire authorisation') and the refusal condition ('Refused, never a silent no-op, once the entry has left pending'), giving clear behavioral guardrails. However, it does not explicitly name alternative tools or state 'use this instead of X', relying on the natural contrast with siblings. This is a minor gap, so 4.

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