prepare_virtuals_tender_v2

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

Annotations only say mutation, non-destructive, idempotent, open-world; the description adds substantial context beyond this: no spend is authorized, FarmDash re-derives output/gas economics server-side, the caller transmits only a local commitment and disclosure manifest, and the specific privileged operations it cannot perform. The auth/tier and deployment-prerequisite disclosures are exactly the behavioral detail annotations cannot carry.

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?

Three sentences plus a bracketed metadata prefix, front-loaded with the core action before the constraints. Density is high but almost every clause carries information (tier, authority endpoint, non-spendability, exclusions). The bracketed capability/API preamble is machine-readable rather than prose and slightly crowds out the action statement.

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 12-parameter, nested-object mutation with no output schema, the description covers safety and intent well but never says what the caller receives back (a draft handle? an evidence object?) or how it feeds authorize_virtuals_tender_v2. The disclosureManifest structure and the approval nonce/expiry pair — the trickiest parts of the call — go unexplained in both description and schema.

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 12 parameters and only 25% schema description coverage, the description must compensate, and it only partially does: it explains that the caller sends a local task commitment (taskCommitmentHash) and disclosure manifest and that simulation ownership is revalidated (simulationId). Roughly nine required parameters — sessionId, agentAddress, sessionToken, idempotencyKey, selectionId, approvalNonce, approvalExpiresAt, maxPaymentUnits — get no semantic treatment, and the commitment explanation largely restates the existing schema description.

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?

The description gives a specific verb and resource — 'Prepare a non-spendable ACP V2 evidence draft' — which is far more precise than the tool name. It also separates this tool from adjacent siblings (authorize_virtuals_tender_v2, reserve_virtuals_tender_funding_v2, record_virtuals_tender_funding_v2) by explicitly saying it 'cannot authorize, create, fund, or settle an ACP job.' 'ACP V2 evidence draft' remains somewhat jargon-heavy, so it stops short of a perfect 5.

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?

It establishes preconditions (deployment prerequisites met, x402-or-subscription tier, authenticated session) and implies a prior simulation whose ownership gets revalidated, which is a clear context for use. The negative boundary routes the agent to the correct sibling for authorization/funding/settlement. It never names which sibling to use next or where this sits in the tender lifecycle, so exclusions are the only routing aid.

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