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

The description discloses that 'Task text discarded' and mentions 'Returns connection methods' but lacks detail on side effects, authentication, rate limits, or the meaning of 'connection methods'. No annotations are present, so the description carries the full burden but fails to provide sufficient transparency.

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 with two sentences, but it is too terse and omits critical details. The structure is adequate, yet the lack of elaboration on key concepts like 'connection methods' and 'task text discarded' makes it less effective.

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 apparent meta-nature (finding a gateway for various task types), the description is incomplete. It does not explain how parameters map to tasks, what the output looks like, or why this tool should be chosen over sibling tools. The absence of an output schema and annotations heightens the need for contextual detail, which is missing.

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?

Although schema coverage is 100%, the individual parameter descriptions are vague and inconsistent with the tool's stated purpose (e.g., 'Git ref name', 'City name for a public weather hint'). They mention 'discarded after the shape check' uniformly, which does not clarify how each parameter contributes to finding a gateway. The descriptions seem copied from generic validation tools and do not meaningfully explain parameter roles.

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 ('Find') and a clear resource ('public pay-per-call tool gateway') with some task examples, distinguishing it from sibling tools that likely provide direct data or checks. However, the mention of 'Task text discarded' introduces ambiguity about the actual operation.

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?

There is no explicit guidance on when to use this tool versus alternatives like weather-hint, normalize-url, or validate-json. The description implies it covers multiple task types, but does not clarify selection criteria or parameter usage, leaving the agent to infer.

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