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

Annotations already cover read-only/idempotent safety, and the description adds genuinely non-obvious behavior: results come in three ordered tiers with different evidence provenance, and filters apply unevenly across tiers. That scoping rule is exactly the kind of thing an agent could not infer and would otherwise get wrong.

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 sentences, front-loaded with the core purpose before the tier detail. The final sentence is long and packs several clauses, but every clause carries distinct information about result ordering or filter scope.

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 and 20 parameters, the description carries the return-value burden and does it well by naming the tiers and their fields (grade, score, x402, agent-ready). It does not address how many indexed/registry results come back or whether limit governs them, a modest gap for a search tool.

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, and the description earns an extra point by disclosing the AND-semantics of q and which filters are honored on which result tiers. It stops short of explaining defaults such as limit applying only to graded listings, which is left to the schema.

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 and a broad but enumerated resource set ('tools, APIs, MCP servers, models and data providers') and immediately clarifies it is a directory search rather than a fetch, distinguishing it from siblings like get_tool and list_capabilities. The three-tier return structure further pins down what kind of result the agent gets.

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?

Explains the matching rule ('every word in q has to match') and routes to /benchmark/ and /categories/ plus list_capabilities for capability ids, which is real usage guidance. It does not explicitly say when to prefer it over get_tool or compare_tools, so the alternative-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.