Quote an evidence pack

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, and the description is consistent with them. It adds genuinely useful behavior beyond the annotations: the price range (1–25 cents), the USDC-on-Base x402 mechanism, and critically the two-step dance where the returned URL must be fetched by an x402 client and paid on retry. That mechanics disclosure is the reason this scores above baseline.

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-loading is good: price and the non-payment caveat come first. But the body is one ~250-word run-on paragraph with deeply nested parentheses (e.g. the exit and trace glosses), which is hard to parse. The length is partly justified by 14 enum kinds, but the structure actively hinders scanning.

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 no output schema, the description carries the burden of explaining the return, yet it only sketches what each pack contains conceptually and never describes the response shape (the returned URL, the 402 payload). Given the tool's complexity and 14 kinds, this is adequate but leaves a real gap around what the agent actually receives.

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 67% and the schema lists the 14 kind enum members with no per-value descriptions, so the description is doing real work by explaining what each kind returns (precheck, drain, exit, trace, counterparty, venue, etc.). It also ties payto to precheck in prose. It does not fully pin down the id parameter's accepted forms beyond the schema's "token id, slug or wallet".

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+resource (quote an evidence pack), gives the price range and payment rail up front, and explicitly says what the tool does NOT do ("This tool does not pay"), which distinguishes it from an actual fetch/pay tool. However, it never names a sibling tool, so the agent must infer how it relates to neighbors like agent_statement, counterparty_preview, or pay_check despite clear topical overlap.

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?

Usage is implied rather than stated: the long enumeration of kind values tells the agent what each evidence pack contains, which guides kind selection, and the payment paragraph explains the two-step fetch flow. But there is no explicit when-to-use-this-vs-alternative guidance and no list of when NOT to use it, even though sibling tools cover overlapping topics.

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