build_constitution_audit

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

With no annotations, the description carries the full burden and does reasonably well: it explains that the constitution is a content-addressed SHA-256 document, that receipts commit to its hash, and that the output is a severity-ranked list of violations. It does not state whether the operation is read-only, what happens to receipts lacking the hash, or error behavior, which are meaningful gaps for an audit tool.

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 sentences, each doing distinct work: what it does, what the inputs mean, and when to reach for it. The verb-and-resource statement is front-loaded with no filler.

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?

No output schema exists, and the description does compensate by describing the return as violations ranked by severity. For a two-parameter tool with nested objects, the remaining gap is edge-case behavior (unhashed receipts, empty results, mismatch handling), which keeps it short of a 5.

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%, so the baseline would be 3. The description earns an extra point by explaining the semantic relationship between the two parameters — receipts commit to the constitution's hash — which is not obvious from the schema alone and clarifies why both are required together.

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: 'Audit a VAOS receipt set against a signed AI constitution.' The follow-up sentences sharpen what the audit produces (receipts violating constitutional articles, ranked by severity), which clearly separates it from sibling builders like build_annex_iv or build_soc2_evidence that produce evidence rather than evaluate it.

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?

'Use it when you want to prove (or disprove) an autonomous agent followed its policy' gives a clear motivating context for invocation. It does not name an explicit alternative or a when-not condition, though the prerequisite (needing a signed constitution) is only surfaced in the schema, not the description.

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