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

Substantially exceeds the annotations by disclosing partial-failure and billing semantics: separate invoices per stage, completed stages stay consumed if a later stage fails, and no atomic bundle charge or automatic transfer. Combined with the destructiveHint=true, this tells the agent exactly what a mid-workflow failure costs. It also surfaces a mandatory consent gate, which annotations do not 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 effort is front-loaded: the purpose comes first, then the sequence and cost, then the failure and billing constraints. It is dense but almost entirely earned. The a -> b ($15) notation is compact, but the $15 is repeated before it pays off, making it less readable than the prose around it.

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?

With 5 parameters, nested objects and no output schema, the description covers sequencing, cost, consent and partial failure well. The main gaps are that it does not say what each stage returns or how a partially completed run's results are surfaced to the caller, which matters for a destructive, charged, multi-stage tool.

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?

At 60% schema coverage, the description adds real meaning: it explains that the risk-stage output serves as negotiation context, which maps to the negotiation stage's knowledgeContext parameter and clarifies a non-obvious data flow. The per-stage invoice wording also clarifies paymentInvoiceIds. It does not address maxChargeUsd or idempotencyKey, though the schema largely covers those.

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 names a specific two-stage operation — risk review of buyer-supplied supplier evidence, then negotiation prep using the review as context — with concrete stage identifiers (supplier-risk, negotiation). It is far more than a restatement of the title. It does not differentiate itself from the other *_to_negotiation workflow siblings (knowledge, meeting, renewal), so differentiating from the family relies on the agent's inference from the input evidence type.

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?

The description states a fixed sequence and a clear context for use: buyer-supplied supplier evidence with risk/freshness gaps feeds a negotiation prep. It also makes the per-stage cost explicit ($15 each), which is exactly the information needed to choose. Missing are the exclusions: nothing says when to pick knowledge_to_negotiation or meeting_to_negotiation instead.

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