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

Annotations already declare readOnly/idempotent/openWorld, and the description goes further with token/latency guidance, compact output negotiation, and concrete auth paths (X-API-Key / Bearer / x402 settlement). It loses a point for the trailing dynamic-pricing paragraph aimed at meteora_brief, which is a different tool and adds noise rather than behavioral insight about this search.

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?

Purpose, alternatives, and domain scope are correctly front-loaded, but the tail drifts into transport/auth/signup/pricing documentation, including a meteora_brief pricing rule that has nothing to do with search_products. Roughly a third of the text is operational boilerplate rather than selection-relevant content.

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 does supply the return shape (prices, sources, freshness) and the auth/payment requirements needed to actually call it. Pagination and failure behavior are not covered, which is the main remaining gap for a search endpoint.

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 100%, so the baseline is 3; the description still adds operational meaning by advising limit 3–5 for token savings and explaining simple=true as a minimal-field preset, plus noting queries may be free-text in any language. It does not explain what the limit cap of 50 means in practice or how ordering works.

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?

Opens with a specific verb and resource ("Search connected marketplaces") and states what comes back ("structured offers (prices, sources, freshness)"). It also carves out the boundary against the sibling best_offer in the same sentence, so an agent can pick between them without opening either schema.

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 names the when-to-use case (compare options, browse multiple listings, explore a category/model) and the when-not-to-use case (single definitive cheapest pick → use best_offer). Domain scope (robotics parts, drone batteries, AI hardware) and free-text/any-language input are also given.

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