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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly says 'Task text discarded' and notes each parameter is 'discarded' after a check, signaling that inputs are not persisted. It also mentions in the schema that 'path' involves no disk access. However, it does not cover return format details, side effects, rate limits, or whether it is a read-only operation beyond what is inferred from 'Find' and 'Returns connection methods'.

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 concise, consisting of two sentences with the core intent front-loaded. It avoids redundancy and the behavioral note about task text being discarded is a useful transparency addition rather than filler. While the task examples could be slightly more structured, it is efficiently written.

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 high complexity (9 optional parameters, no output schema, no annotations), the description is incomplete. It does not explain how to choose which parameter(s) to provide for a specific task type (weather, search, scrape, voice). An agent lacks enough context to map a task to the correct inputs, and there is no information about what form the returned 'connection methods' take or any pagination or error behavior.

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 100%, with each of the 9 parameters already described in the schema (e.g., 'City name for a public weather hint; discarded after the call'). The tool description adds no additional parameter semantics, leaving unclear how these diverse parameters (ref, url, city, feed, host, json, path, zone, query) map to the gateway-finding logic. For instance, an agent cannot determine whether city or query is the right input for a weather gateway. Baseline 3 applies because the schema covers each parameter, but the description does not deepen this coverage.

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 states a specific verb and resource: 'Find a public pay-per-call tool gateway' with examples of tasks like weather, search, scrape, or voice. This clarifies it is a meta-tool that returns connection methods, distinguishing it from siblings that perform operations directly (e.g., weather-hint, normalize-url). However, it does not explicitly differentiate from all sibling tools, so a slight ambiguity remains.

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 implies when to use the tool: when you need a connection method for a public pay-per-call tool, rather than performing the task itself. It gives examples of task categories but does not state when *not* to use the tool or how it compares to alternatives like calc-eval or status-catalog. There is no explicit routing to siblings or exclusions, leaving the usage context partially implicit.

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