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

Annotations cover the write/open-world profile, and the description adds substantive context beyond them: the authorization model (agent's bound/proven wallet must equal the market creator), that live kinds are TTL-bounded, coalesced, carry source metadata, and have stale-update protection. It does not address the tension between idempotentHint=false and the required idempotencyKey, nor what happens on a rejected proof, which is the remaining gap.

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 purpose, then authority, then kind semantics — a sensible order that an agent can act on after the second sentence. The trailing 'Examples:' line is a truncated fragment that restates kind=price_chart and adds essentially no information, a small amount of waste.

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 13-parameter, nested-object, proof-bearing mutation with an output schema, the description supplies the parts an agent cannot infer: who is authorized, which kinds are durable versus ephemeral, and that live state is TTL and stale-update guarded. Remaining mechanics (nonce fetch, idempotency key reuse, signature binding) are already spelled out in the schema property descriptions.

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?

With schema coverage at 54%, the description compensates by explaining the semantic split of the kind enum (durable vs bounded live state with TTL/coalescing/stale protection), which the schema's bare enum does not convey. It adds nothing for chainId, marketAddress, label, source, or the observation object, but the schema documents several of those and the nested observation fields.

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 (publish) and a specific resource (market surface data), and the opening clause 'by intent' plus the kind enumeration makes the nature of the payload clear. It does not name any sibling (publish_take, post_canvas_update, push_content) or explain how it differs from writing content through those tools, so differentiation is left implicit.

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 real selection guidance at the parameter level: kind=note for durable creator content, price_chart/scoreboard/ticker for bounded live state. However, there is no guidance on when to choose this tool over the other publishing siblings, no stated preconditions besides the creator-wallet rule, and no note on what this tool cannot do.

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