provenance_preview

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

With no annotations, the description carries the full burden and discloses the key behavioral traits: read-only operation, no spend decision recorded, the specific attestation fields returned, and that China-origin families are flagged. It stops short of covering error behavior, authentication needs, or return formatting, but the core safety profile and output scope are clearly stated.

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 with a front-loaded purpose and the no-spend guarantee placed first. The final sentence slightly overlaps the first ('WITHOUT spending' vs 'without recording a spend decision'), but each sentence otherwise earns its place by covering outputs, parameter constraints, and cross-tool behavior.

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 read-only preview tool with no annotations and no output schema, the description covers the essential ground: what is previewed, the cost-safety property, the identifier-only constraint, and the relationship to spend_decide. It could go further by describing how China-origin flagging manifests in the output and the role of endpoint_url, but nothing needed for safe invocation 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 real meaning beyond the schema for the optional IDs — 'accept identifiers only' and the fact that spend_decide signs them into the actor fields — which goes beyond the schema's $ref descriptions. However, it adds nothing for model or endpoint_url, which are the two parameters lacking schema descriptions, so the 60% coverage gap is only partially compensated.

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 and resource ('Preview the provenance AgentGuard would attest') and enumerates exactly what is previewed: model identity, weights origin country, hosting jurisdiction, retention posture. The emphatic 'WITHOUT spending' distinguishes it from the sibling spend_decide, so an agent can tell them apart without inspecting schemas.

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 gives clear context for when this tool fits — checking provenance with no spend commitment — and contrasts it with spend_decide, which binds identifiers into the signed actor. It also notes that read-only and cost-configuration tools accept these fields without recording a spend decision. However, it never explicitly names an alternative or states a when-not-to-use condition, leaving routing to inference.

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