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

Annotations already declare readOnly/idempotent/non-destructive, and the description is consistent with a prepare tool that emits MESSAGE_TO_SIGN and BODY_JSON rather than mutating state. It adds real context the annotations cannot convey: hashes not held by the board are refused before signing, photos arrive by reference not through the conversation, the call is free with no gas, and the signer's key is never held by the house. Minor deduction only because cost/signer information is stated twice.

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 core flow is front-loaded, but the text is long for a 7-parameter prepare step and repeats itself: 'FREE when signed' is restated as 'Cost and signer: free, no gas', and the photos-by-reference rule appears twice. The aside about an assistant handing in 'a photo nobody took' is vivid but not load-bearing.

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 everything an agent needs for a two-step signing flow: prerequisites, the out-of-band photo upload path, hash validation, the 5-minute submit window, who signs, and who adjudicates. Return values are summarized even though an output schema already exists, so nothing material 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?

Schema coverage is 100%, so baseline is 3, but the description adds behavioral meaning beyond the schema: the default photoHashes set is what the board already holds, caller-supplied hashes are validated against that set and refused pre-signature, and gps must be captured on-site because stored location is never read back. It does not mention revisesProofId, which the schema covers on its own.

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 ('record them on the physical proof rail so a human can review them against the packet's checklist') and situates it precisely as step 1 of 2, after submit_proof and before submit_physical_proof. An agent can distinguish it from submit_proof and submit_physical_proof without opening any schema.

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 explicit sequencing (after submit_proof hands in photos, then sign, then call submit_physical_proof within 5 minutes), names the prerequisite command (`node vealth-agent.mjs proof-photo ...`), and states the exclusion that a human, never the caller, renders the verdict. Alternatives and ordering are spelled out rather than implied.

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