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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds context beyond these: it explicitly states the tool is 'free', returns an 'exact HTTP request', and 'never signs, pays, or retries the paid create'. This clarifies the operation's side-effect-free nature and its output format, which is useful beyond the annotation flags. No contradiction with annotations.

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 two sentences with zero filler. The core action ('Validate and return the exact free HTTP request') is front-loaded, followed by the relevant scenario and a clear statement of what the tool does not do. Every sentence earns its place.

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 tool with no output schema, the description clearly states that it returns an 'exact free HTTP request', which indicates the return type. It explains the recovery use case and the limits (only confirmed-settlement watches). It doesn't specify the HTTP request format or error handling, but given the parameter schema already documents inputs, this is adequate. Slight gap: it doesn't state what happens if the watch is not recoverable, but the phrase 'Validate and return' implies validation errors might surface.

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%, and each parameter already has a descriptive explanation and constraints (e.g., idempotencyKey, atomicAmount, addresses). The description does not add any parameter-specific semantics beyond the schema, so the baseline of 3 is appropriate when the schema carries the full burden.

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 states a specific verb ('Validate and return') and resource ('exact free HTTP request used to recover an existing watch'), with a clear trigger scenario ('after a paid create may have succeeded but the caller lost the returned watchId'). It also differentiates from siblings by focusing on recovery rather than creation (prepare_watch) or querying (get_watch), making tool selection 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 specifies precisely when to use this tool: when a paid create may have succeeded but the watchId was lost. It also notes that confirmed-settlement watches remain recoverable even after terminal expiry or indeterminate completion. It does not explicitly name alternatives or exclusions (e.g., 'use prepare_watch for new watches'), but the recovery scenario is clear enough to guide an agent.

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