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

Goes well past the annotations: it discloses the exact side effects (manifest, watermark, ISCC registration, timestamp), clarifies idempotency semantics (same asset id, no second record), warns that profiles are beta and not a compliance guarantee, and states the billing rule (0.01 USDC per image, failed calls never charged). This is the kind of cost, safety, and side-effect detail an agent needs before invoking a mutating 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?

Front-loads the action and the produced artifacts, then layers in idempotency, caveats, size limits, and pricing in descending order of importance. Dense but every clause carries information; only the parenthetical about REST-vs-MCP return mechanics is somewhat incidental.

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 10-parameter mutation tool with no output schema, it covers return shape ('the marked file'), idempotency, pricing, and file-size routing, which is close to complete. The one gap is the inconsistency between the 1 MiB inline limit in prose and the 4 MiB max in the schema, which could cause a wrongly sized request.

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 already 90%, so the baseline is 3, but the description adds meaning by clarifying that the AI profiles always watermark (versus provenance-only where invisible_watermark is opt-in) and by pointing at GET /v1/provenance/profiles for profile semantics. It also introduces a confusing size rule ('up to 1 MiB inline') that conflicts with the schema's stated 4 MiB base64 limit, which keeps this below a 5.

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 ('Marks an ... image with a compliance profile') and enumerates exactly what marking produces: a signed C2PA manifest, an invisible watermark, an ISCC fingerprint registered with Proofestry, and a timestamp. That artifact list clearly separates it from read-only siblings like detect_provenance and verify_provenance.

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?

Gives concrete usage context: profiles are beta until the signer is on the C2PA trust list, profiles help meet obligations but do not guarantee compliance, and larger files must go through the upload job routes instead of inline. It never names a sibling tool to use for verification afterward, so the alternative routing is only partial.

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