billy_execute

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

Goes well beyond the annotations by disclosing that authorization is required, that an authorization note is only an audit assertion rather than user consent, and that unknown outcomes block subsequent writes. These are operational behaviors an agent must know to act correctly, and they are not present in the structured 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?

Three terse sentences, with the core action front-loaded. Each sentence adds necessary operational guidance; there is no filler or repetition.

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?

Covers purpose, prerequisites, and safety behavior, but leaves gaps: expectedHash is unexplained, the meaning of 'unknown outcomes' is undefined, and there is no output schema or return-value description. For a destructive tool with three required parameters and zero schema descriptions, this is incomplete.

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 0%, so the description must compensate for all three parameters. It relates planId to the 'proposal' and authorization to the 'authorization note', but never explains expectedHash or how it is used (e.g., verifying exact plan content). The name 'expectedHash' is suggestive but the description does not clarify 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 ('Execute the exact reviewed proposal once'). The phrase 'reviewed proposal' distinguishes this from planning/status siblings (billy_prepare, billy_plan, billy_status) by naming the execution step. It also specifies a one-time action, clarifying scope.

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?

Provides concrete prerequisites ('Requires authorization... and locally enabled writes') and a strong guardrail ('Unknown outcomes block further writes; never work around them'). It does not explicitly name sibling alternatives or state when not to use it, but the execution-versus-planning contrast is clear from the verb and resource.

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