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

Annotations already cover read-only, idempotent, open-world, non-destructive, so the description earns credit for what they don't say: that the returned workType/standard/location/proofHash/paymentTxHash/token fields are attacker-controlled text and arrive fenced. It also flags that possibleNextSteps is non-authoritative — a genuinely useful behavioral caveat. The final 'Cost and signer: free and keyless, nothing to sign' sentence merely restates the opening and earns nothing.

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 and scope, and the trust/warning content is placed after the core capability, which is the right order. The one flaw is the closing 'Cost and signer: free and keyless, nothing to sign', which repeats the third sentence verbatim in substance.

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?

Because an output schema exists, the description correctly doesn't enumerate return shapes, and it does cover the two things the schema can't: the untrusted-field fencing and the authority relationship to prepare_chain_step. Only minor gaps remain, such as behavior for a nonexistent workId or per-chain differences.

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 exceeds it by explaining what the optional wallet actually yields — your role (creator, claimant, owner, or none) plus candidate next steps — which the schema's one-line hint does not convey. Chain and workId semantics are left to the schema, which already handles them adequately.

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 ('Read one job straight from the public EWP contract') and names the exact scope (Base or Robinhood Chain), then enumerates the returned fields (status, price, standard, location, poster, claimant, proof hash, payment record). An agent can distinguish it from chain-write siblings like prepare_chain_step and submit_* without opening the 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?

'Free, keyless, no wallet needed' and the optional-wallet clause make the calling context clear, and the description explicitly defers authority to prepare_chain_step for next-step validation. However, it never states when to prefer this over lookalike siblings such as work_status, get_work_packet, or find_work, so the routing decision is left implicit.

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