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

No annotations are provided, so the full burden falls on the description. It adds genuinely useful behavioral facts: task text is discarded and only connection methods are returned. It partially contradicts itself, though – if the task text is discarded, how does the tool 'find a gateway for a task'? The schema's parameter comments add 'discarded after check' detail, but the description itself leaves the core mechanism unexplained. No contradiction with annotations exists since none were supplied.

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 tight two-sentence definition that front-loads the purpose and names the return value. The closing sentence 'Task text discarded' is efficient but ambiguously placed – it is unclear whether 'task text' refers to the whole request payload and undermines the purpose statement that precedes it.

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?

This is a 9-parameter, heterogeneous tool with no output schema and no annotations, so the description carries a heavy completeness burden. It explains what is returned ('connection methods') but not their form, does not reveal how the tool selects a gateway or what shape checks are performed, and gives no guidance on selecting among the nine parameters. An agent would need substantially more context to invoke it 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 100%, so the baseline of 3 applies. The schema already documents each parameter's meaning (e.g., 'Git ref name; discarded after the shape check'), and the description adds no further semantic detail about parameters. The description's mention of tasks like weather and search loosely maps to 'city' and 'query', but it does not explicitly connect any task to a parameter.

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 clear verb ('Find'), a specific resource type ('public pay-per-call tool gateway'), and concrete task examples (weather, search, scrape, voice). It also discloses the return value ('connection methods'). However, 'tool gateway' is an unconventional concept that is not elaborated, and the description does not distinguish this elastically-scoped tool from its 27 siblings, which all appear to be named shape/fetch/validation checks.

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 examples (weather, search, scrape, voice) give implicit context for when this index might be useful, but there is no explicit when-to-use vs when-not-to-use guidance and no mention of alternative tools. More critically, with 9 heterogeneous optional parameters, the description gives no hint about which parameter an agent should fill for which task – an agent cannot tell whether to pass 'city' or 'url' or 'query' to route a given request.

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