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

Annotations already declare readOnlyHint=true, and 'Read-only' merely restates that. The useful added context is the return shape (endpoint, price, payment method, auth, docs), which is valuable since no output schema exists, but nothing about ranking, result caps, or coverage of the directory is disclosed.

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?

Two sentences, zero filler: the first states what can be searched, the second what comes back, and the read-only note is tacked on last. Front-loaded and appropriately sized.

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?

Listing the returned fields compensates for the absent output schema and the read-only profile is covered by annotations, but with six parameters at 33% schema coverage the definition leaves the agent guessing about the filter parameters it will need to call this correctly.

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 only 33% — q and max_price are documented in-schema while kind, payment, category, and limit are bare. The description names none of these filters and gives no guidance on how keyword matching interacts with them, so it does not compensate for the gap.

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?

Names a specific verb (Find) and an unusually concrete resource inventory: APIs, x402 pay-per-call endpoints (USDC on Base), and MCP servers, matched by keyword. It is clearly a broad search rather than a single-record fetch like get_service or a taxonomy listing like list_categories, though it does not name those siblings explicitly.

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 keyword-search framing implies when this tool applies, and 'find' vs. the sibling name get_service hints at browse-then-fetch, but no explicit when-to-use, when-not-to-use, or hand-off guidance is given.

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