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

The description discloses genuinely useful behavior (cost billed to credits, failed attempts refunded, sequential fallback up to the fallback limit), but it directly conflicts with the structured annotations: a tool that executes real tasks, spends credits, and whose own example label is "book the reservation" is declared readOnlyHint=true and destructiveHint=false. That is an annotation contradiction under the scoring rules.

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?

Front-loaded with the core mechanic, then billing, then long-task handling, then dry_run and the prerequisite. Every sentence carries information; it is slightly dense but not padded.

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, the description supplies the key return semantics (route_id, refunds on failure, pay only for the completing agent) and the follow-up tool. It does not describe what the successful task result itself looks like, which is the main remaining gap for a 7-parameter executor.

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 71%, and the description still adds meaning the schema lacks: dry_run is defined as showing the ranking without executing anything, and route_id is explained as the handle for get_api_task. fallbacks and prefer remain defined only by the schema/enum, but the description carries the semantically ambiguous parameters.

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?

"Give a task and StartupHub picks the agent to run it" names a specific action and resource, and the ranking/fallback explanation makes clear this is a router/executor rather than a direct API caller like call_api. An agent can distinguish it from find_apis (discovery) and get_api_task (retrieval) without opening any schema.

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?

It gives concrete selection context: use dry_run to see the ranking without running, use get_api_task with the returned route_id for long tasks, and a free account is required. It does not explicitly contrast with call_api for cases where you already know which API to call, so the when-not guidance is incomplete.

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