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

With no annotations present, the description carries the full behavioral burden and does so thoroughly. It discloses the paid nature, the 402 challenge flow, preview behavior, NOT_DEPLOYED behavior, the uncheckability of watermarks without public detectors, and the point-in-time scope. This goes well beyond a generic call description.

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 dense and information-rich, with the critical PAID status and payment flow front-loaded. Every sentence contributes behavioral or semantic detail rather than padding. It loses a point for a slightly awkward run-on opening that mixes the endpoint, the pack definition, and evidence components into one long sentence.

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?

Despite having no output schema and no annotations, the description explains the return contents, the free preview return, the 402 failure mode, the NOT_DEPLOYED failure mode, and the boundaries of interpretation. For a complex paid measurement tool with five parameters, this is unusually complete and leaves little ambiguity about expected behavior.

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 schema already covers all five parameters with 100% description coverage, establishing a baseline of 3. The description adds meaningful context on top: x_payment comes from signing against accepts[] from the prior 402, preview=true returns the same measurement unsigned, and manifest_b64 relates to a detached C2PA manifest store. This enriched context helps an agent select and format parameters correctly.

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 the tool returns an 'Article 50 marking-evidence pack' that measures whether a machine-readable mark is detectable in supplied bytes, and lists the evidence components. It names the exact endpoint and distinguishes its scope from a conformity or compliance opinion. However, the phrasing is more noun-like than an explicit verb+resource statement, and it does not directly differentiate itself from sibling evidence tools like rwa_evidence.

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 clearly explains the payment workflow: it is paid via x402 or invoice, preview=true is free, omitting x_payment yields the 402 challenge, and an undeployed route returns NOT_DEPLOYED. It also states strong when-not conditions: the result is point-in-time detection and 'never a conformity opinion' or compliance statement. It does not, however, name sibling tools or say when to prefer this over them.

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