find_best_service

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it excels. It details the ranking weights, the compliance cap (0.6 floor), the conservative undercount of traction, pro-quota attribution for shared payTo addresses, renorm when terms are missing, the 30-day settlement recency requirement, and that top_buyer_share_30d does not enter the score. It even discloses versioning incomparability (ranking_version 2 vs 1), which is a subtle behavioral caveat an agent must know.

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?

The description is a single, dense paragraph that contains a great deal of necessary nuance, but it is not structured for scanning. It front-loads the core purpose, yet the long sentences and parentheticals (e.g., 'a fact about the payment envelope, not a judgement on the service') make it harder to parse than it could be. Every sentence does earn its place, but the wall-of-text format hurts conciseness.

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?

Given the tool's complexity (8 optional params, no output schema, no annotations), the description is exceptionally complete. It covers the core return concept (ranked recommendations), the specific output fields (top_buyer_share_30d, ranking_version), the optional facilitator context flag, and the behavior of missing/renormalized weights. An agent can fully anticipate what the tool will do and return without needing additional documentation.

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?

The input schema already provides 100% parameter descriptions, well above the 80% threshold for baseline 3. The tool description adds no further detail about parameter semantics—it only restates concepts like 'filtered by category and network' that the schema already covers. Since schema does the heavy lifting, baseline 3 is appropriate; the description doesn't need to repeat parameter-level syntax.

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 opens with a specific verb+resource: 'Recommend the best x402 service(s) for a need.' It then enumerates ranking criteria (reliability, compliance, price, traction) and filters (category, network), making the tool's role unmistakable. This clearly distinguishes it from sibling tools like search_x402_services or get_service, which are about discovery and retrieval rather than ranked recommendation.

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 description establishes clear context: use this tool when you have a need and want a ranked recommendation, with optional filters. It explains the default behavior and the 'prefer' tie-breaking emphasis. However, it never explicitly states when NOT to use this tool or names alternatives, so it falls short of full guidance; it doesn't say 'for raw search use search_x402_services' or exclude cases where the ranking logic is undesirable.

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