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

Adds context the annotations do not carry: invocation incurs cost only when data is returned, so empty results and failures are free, and an account link is required. Annotations do declare readOnlyHint=true, so the description rightly focuses on the billing side effect rather than safety, but it says nothing about rate limits or error behavior beyond the free-on-failure rule.

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?

Two tight sentences, front-loaded with the action and return payload, followed by the account requirement and cost rule. No filler or restatement of the tool name.

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 usefully names the billing fields returned alongside data and covers the prerequisite and cost model. It omits what a caller should expect on invalid endpoint_id or what 'data' looks like, but is otherwise sufficient to invoke 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 schema already documents both endpoint_id (with an example) and params. The description adds no parameter-level meaning beyond what the schema provides, which is the expected baseline when the schema does the work.

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?

Uses a specific verb and resource ('Run an endpoint and return its data plus billing info') and names the concrete return fields charged_usd and remaining credit. It does not explicitly say how it differs from the sibling get_endpoint (which only reads metadata without executing), leaving the run-vs-inspect distinction to be inferred.

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?

States one real precondition — a Qovia account must be connected to this server — and implies usage by mentioning get_endpoint for parameter discovery. It does not say when to choose this over get_endpoint or search_endpoints, nor when to avoid calling it given the billing cost.

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