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

Adds significant behavioral context beyond annotations: verifier sandbox, evidence bundle outcomes, size/rate limits, and the test-only environment. Annotations only give hints, so this description fully discloses operational behavior and side effects.

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 concise sentences, front-loaded with the main purpose, then key details. No fluff; every clause adds information. Ideal length for the tool's 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?

Covers the core aspects: content passing, auth modes, verification behavior, limits, and test environment. Lacks explicit guidance on obtaining job_id or the exact signature format, but the schema covers that. For an agent, the description is sufficient to call it correctly.

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 has 100% coverage with descriptions for each param, so baseline is 3. The description adds value by explaining the two auth modes (address/signed_request vs wallet_handle), that sha256 is auto-computed, and that content_text/content_b64 are alternatives. This goes beyond the schema.

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 action (submit deliverable), the HTTP endpoint, and the roles (provider). Clearly distinguishes it as the final submission step for a job. Though it doesn't explicitly contrast with afg_upload_artifact, its scope is unambiguous.

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?

Describes two usage modes (session wallet vs bring-your-own-wallet) and how to pass content, but does not explicitly state when to prefer this over afg_upload_artifact or other siblings. The 'TEST MONEY ONLY' warning and 'provider submits' context imply the appropriate scenario.

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