recommend

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

Without this sentence the agent would assume a plain lookup; instead it learns that payment may occur, that it requires owner opt-in, that it consumes the process's single authorization irreversibly, and that there is a USDC cap. That is strong non-obvious disclosure consistent with readOnlyHint=false and idempotentHint=false. It stops short of saying what happens if opt-in is missing or the fee exceeds the limit.

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 with the discovery capability front-loaded and the payment/auth constraint second. Dense but every clause adds information; 'up to the configured USDC limit' is the only mildly vague phrasing.

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?

There is no output schema, so the description must convey return shape — 'URLs, prices and call details' does so only at a high level. The payment and authorization consequences are well covered, but the six-parameter input surface is largely unaddressed, leaving the agent guessing on most call arguments.

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 17% — five of six parameters (need, live, view, chain, limit) have no schema description and no mention in the prose. The description hints at output richness ('URLs, prices, call details') which loosely relates to the view enum, but it never explains need format, the chain identifier pattern, the limit cap of 5, or what 'live: 1' does. It does not compensate for the coverage gap.

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 clear verb+resource: it finds APIs matching a stated need and returns URLs, prices, and call details. This is much more specific than the opaque name 'recommend'. It does not, however, contrast itself against its siblings (inspect, receipt, health), so the agent must infer the boundary.

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 phrase 'for your task' implies the general context but states no when-to-use or when-not-to-use conditions. Nothing tells the agent how this differs from 'inspect' (presumably for a single already-known API) or when to prefer receipt/health.

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