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

Annotations declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, but the description advertises calling arbitrary third-party APIs with 'METHOD /path' plus body and gives the example 'book the reservation' — plainly state-mutating and open-world. The description directly undercuts the safety annotations an agent would otherwise rely on for approval decisions.

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?

Purpose is front-loaded and every clause adds information (mode formats, follow-up tool, credits, account requirement). It is telegraphic and run-on ('REST: ... MCP: ... Chat: ... Agent: ...'), which costs a little readability but not content value.

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?

For a 10-parameter generic proxy with no output schema, it covers billing, the free-account prerequisite, the task_id follow-up path and optional provider key. It does not cover error behavior, rate limits, or whether methods like GET vs DELETE behave differently — relevant given the destructive potential.

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 30%, but the description compensates by explaining the operation string per mode (REST 'METHOD /path', MCP tool name + arguments, chat model id + messages, agent task), how path/query/body and label apply, and when provider_key is needed. Remaining gaps are structural detail of the free-form body/query objects, which the schema types only loosely.

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?

States a specific verb and resource (call any API, MCP server, chat endpoint or agent listed on StartupHub) and enumerates the four invocation modes with their operation formats. An agent can distinguish this from find_apis (discovery) and get_api_task (follow-up) without opening the 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?

Explicitly routes discovery to find_apis, long agent tasks to get_api_task, and constrains provider_key to 'only when the listing needs your own key'. Lacks an explicit statement of when not to use it or what happens for unsupported listing types, so not a full 5.

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