get_verification_artifact

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

Despite annotations already setting readOnlyHint and idempotentHint, the description adds context: it's an in-memory lookup with a 15-minute lifetime, deliberately omits certain outputs to prevent echo, and is read-only. This goes beyond 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 a single paragraph but is informative and front-loaded with the main purpose. It could benefit from better structure (e.g., bullet points) but is not overly verbose for the complexity.

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?

Given the tool's complexity, annotations, and no output schema, the description fully covers what is included, omitted, the intended use case, lifespan, and error checks. It provides sufficient context for correct agent 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?

The single parameter 'handle' is described in the input schema as 'Opaque handle returned by any prepare_* tool.' This adds meaning, but the overall description doesn't provide additional detail about the parameter beyond what the schema already states. Since schema coverage is 100%, baseline 3 is appropriate.

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 specifies the tool returns a sparse verification artifact for a prepared tx, listing exact contents like raw calldata, chain, to/value, payloadHash, and preSignHash. It clearly differentiates from sibling tools by emphasizing adversarial independent verification.

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 explains when to use it: after any prepare_* tool for adversarial independent verification, with a second LLM session. It also states when not to rely on it (disagreement or preSignHash mismatch) and that it's read-only with no external API calls.

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