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

With no annotations, the description carries the full burden of behavioral disclosure, and it communicates key traits: the transaction is unsigned, the server never sees a key, revoke is effective immediately once confirmed, and reclaim is CLTV-gated. It also discloses that the agent cannot stop or outrun a confirmed revoke. This is strong coverage, though it does not describe error conditions or returned data shape.

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 front-loaded with the essential action and then expands into the two modes, key safety, and intended use case. Every sentence adds semantic value, though the phrasing 'cannot outrun it beyond the limits it already had' and the uppercase safety line add rhetorical emphasis rather than new 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 moderately complex builder with nested objects and no output schema, the description is nearly sufficient: it explains purpose, the two operational modes, timing guarantees, and key handling. It does not explicitly describe the returned unsigned-transaction shape or clarify how `feeSompi` and `computeBudget` should be chosen, but nothing essential to selecting the tool or invoking the main parameters is missing.

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?

The description adds meaningful semantics to the `kind` parameter by explaining what revoke and reclaim do and which key signs each, and it reinforces `lockTime` via the CLTV window. However, with only 50% schema description coverage, the optional `feeSompi` and `computeBudget` parameters receive no added context, and many nested grant fields are left to their names.

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 specific, concrete action: 'Assemble an unsigned transaction that ENDS this grant and sweeps its balance to the principal.' This precisely identifies both the resource (the grant) and the outcome (ending it), and clearly differentiates it from sibling builders like warda_build_spend or warda_build_settlement, which would not terminate the grant.

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?

It explicitly frames when to use it: 'the tool a monitor calls when a grant is behaving badly and something has to act.' It also separates the two modes—revoke for immediate emergency stop, reclaim for after the window has closed—and even notes that an early reclaim 'simply will not run.' It does not name sibling alternatives explicitly or state when not to use this tool beyond those timing constraints.

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