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 them while adding substantial context: it reads live chain state and refuses with a plain reason, it eth_calls the exact transaction from the wallet as a final simulation, it never holds a key or pays gas, and it discloses that location is written publicly and permanently and that price is stored in cents. Those are exactly the behavioral traits annotations cannot convey.

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 purpose and the no-custody guarantee are front-loaded, which is good, but the block is long and carries rhetorical filler ("this is how a stranger's own AI runs the whole job loop ... with no house involved and no house money") and repeats the no-key point twice ("never holds a key" and "the house never holds a key"). The step-to-field mapping is the genuinely valuable part and is buried mid-paragraph.

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 14-parameter, multi-step transaction builder this covers everything an agent needs: both chains, all eight steps, per-step required fields, the pre-flight refusal behavior, the signer/payer model, and the on-chain permanence warning. An output schema exists, so return-value explanation is correctly omitted.

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 the baseline is 3, but the description adds meaning beyond the schema by mapping which extra fields each step consumes (post: workType/standard/priceUsd/location/expiresInDays; proof: workId+proofHash; settle: paymentTxHash/tokenContractAddress/tokenId/qualityScore) and by explaining semantics such as the WorkType bucketing, the "native" sentinel, and that settle is a receipt rather than a payment.

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?

Specific verb and resource: "Build the exact unsigned transaction for one step of a real ecological-work job's lifecycle", with the eight steps enumerated and both chains named. An agent knows exactly what comes back (an unsigned tx, not a broadcast). It does not, however, distinguish itself from similarly named siblings such as prepare_post_work, prepare_proof, or prepare_claim, so the agent must infer which of those to use from outside the description.

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 a concrete prerequisite ("Call chain_work_status first if you are unsure of a job's current state") and states the cost model ("free to prepare; the person's own wallet signs and pays its own gas"). It explains when the tool will refuse (paused contract, wrong status, unauthorized wallet), which is useful context. It lacks explicit guidance on when to choose this over the prepare_proof / prepare_post_work siblings.

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