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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower; the description still adds real context beyond them by clarifying the tool is free, does not execute a payment or assume budget approval, and that a no-match outcome resolves to DO_NOT_BUY. It stops short of describing the shape of a successful recommendation payload, but the routing-relevant behavior is well covered.

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?

Front-loads the core purpose and scoping constraint before the routing alternatives, so the most important sentence comes first. It is dense with several sibling references, but every clause carries routing value and nothing is redundant padding.

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 one-parameter, read-only recommendation tool with no output schema, the description supplies the missing pieces an agent needs: the free/no-payment nature, the terminal DO_NOT_BUY signal, and which sibling to pick for adjacent scenarios. The only minor gap is that it references enterprise-commerce-control-tower and agent-commerce-command-center, which do not appear in this sibling list, potentially leaving the agent unable to resolve those suggestions.

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 description coverage is 100% and the single 'goal' parameter is fully documented with its own example, so the description's repeated example ({goal:'verify an x402 seller before paying'}) adds little beyond the schema. Baseline 3 is appropriate when the schema already carries parameter meaning.

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?

States a specific verb (recommend) and resource (paid agent tool / product) plus the mechanism (free, plain-language goal). It is immediately differentiable from the quote_* and list_* siblings because it explicitly frames itself as a single-tool recommendation rather than a quote or listing.

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?

Explicitly scopes when to use it ('one specific agent task, not to assume budget approval or execute a payment') and names concrete alternatives with their selecting conditions: enterprise-commerce-control-tower for multi-workspace settlement, agent-commerce-command-center for single-workspace reconciliation, quote_premium_delivery before expensive analysis, quote_premium_workload for volume discounts. This is textbook when/when-not/alternatives routing.

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