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

Goes well beyond the annotations: signer must be the same wallet that claimed, 5-minute validity window, free/no gas, house never holds a key, and the write gate rejects non-probed paths. The only soft spot is 'Atomic: readers see the old set or the new set, never half,' which describes the eventual surface state rather than this prepare step, an ambiguity given readOnlyHint=true — though it does not truly contradict the hint since this tool only returns a message to sign.

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-loaded with the action and ordered as action → payload rules → next step → cost/signer, with no filler sentences. It is dense to the point of being run-on in places (the resource-payload sentence packs three rules), but every clause carries information.

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 5-required-parameter tool with prerequisites and a two-step sign/submit flow, the description covers ordering, signer identity, timing, cost, and the gating constraint. An output schema exists, so return values need not be explained — the brief mention of MESSAGE_TO_SIGN/BODY_JSON is redundant but harmless.

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; the description earns a bump by pinning down resources semantics (path must be exactly a path the packet checks, contentType is application/json, body is the JSON text authored) and by tying workerWallet to the signing requirement ('SAME wallet that claimed'). Size limits and the other ids are left to 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 concrete verb and object — publish the JSON files the packet's definition of done probes — and frames it explicitly as 'step 1 of 2' whose counterpart is submit_evidence_write. An agent can distinguish this from prepare_evidence_surface and submit_evidence_write without opening a 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 the precondition ('After your claim binds the surface'), the follow-up route ('then call submit_evidence_write within 5 minutes'), and the exclusion rule ('the write gate refuses any other' path). Both when-to-call and what-to-call-next are explicit.

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