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

Annotations already declare readOnlyHint=true and openWorldHint=false, so 'Read-only' and 'No payment' largely restate structured data. The genuinely additive detail is that quotes may be 'indexed or live', hinting at differing cost/latency, though this also sits in mild tension with openWorldHint=false and no latency, caching, or rate-limit behavior is described.

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?

Two tight sentences plus two short fragments, front-loaded with the core action and return payload. Minor waste in repeating the annotation-backed 'Read-only' claim as a standalone fragment, but no padding overall.

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?

An output schema exists, so the enumerated return fields are a bonus rather than a necessity, and the read-only safety profile is covered by annotations. However, with a nested six-field constraints object left entirely unexplained and no note on quote freshness, cost, or whether budget is needed for pricing, the definition leaves meaningful gaps for a moderately complex 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?

Schema coverage is only 33%: only 'budget' carries a description (USDC base units, 6 decimals). The nested 'constraints' object with six sub-properties (limit, claimed, network, minScore, protocol, includeUnpriced) is undocumented in both schema and description, and the description says nothing about the semantics of the 'task' string or how 'delivery score' relates to minScore.

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 uses a specific verb and resource ('Takes a task and budget; returns ranked candidate sellers') and enumerates the key outputs (quote, request shape, delivery score, order modes), which clearly separates it from a plain lookup like find_service or a mutation like place_order. It stops short of naming a sibling, but the action is unmistakable.

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?

'No payment. Read-only.' implicitly signals this is the discovery/pre-quote step before place_order, but it never states that explicitly, nor does it give prerequisites such as whether a budget is required to obtain quotes or when indexed vs live quotes are appropriate. Usage is inferable rather than stated.

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