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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely non-obvious behavior: shared cache semantics, a $0.005 USDC x402 charge per call, and no charge when nothing close enough is cached. It does not describe latency or what a hit-vs-miss response looks like, but the cost/charge disclosure is substantive.

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?

Three short sentences, front-loaded with the identity of the tool, then pricing and cache-miss behavior. The x402 price sentence is slightly redundant with 'a quarter of the price' but still adds concrete cost information.

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 read-only paid lookup with no output schema, the description covers what is returned (a cited answer), its source, the pricing model, and the miss behavior, which is what an agent needs to call it correctly. Only marginal gaps remain, such as freshness bounds beyond the max_age_days schema field.

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 67%, with max_age_days and min_similarity documented in the schema itself. The description's 'nothing close enough is cached' implicitly explains the role of the similarity threshold but adds no syntax, range, or default detail beyond the schema, so baseline 3 applies.

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 ('shared answer cache' returning 'a recent cited answer') and its provenance ('from /v1/answer'), which clearly separates it from a fresh `answer` call. It stops short of naming the sibling tool directly, so an agent must infer that `answer` is the non-cached counterpart.

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?

Gives clear selection context: it is the cheap variant of /v1/answer ('a quarter of the price') and is not charged on a cache miss, which tells an agent when the tradeoff is favorable. It lacks an explicit 'use this when X, use answer when Y' exclusion, so the routing is implied rather than stated.

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