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

Annotations declare openWorld=true, readOnly=false, idempotent=false, but say nothing about what a call actually does at the boundary. The description adds two non-obvious behaviors: unpaid/paid agents yield a payment path rather than a result, and the returned text is the publisher's own untrusted content that must not be followed as instructions — a valuable prompt-injection warning not available anywhere else.

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?

Three short sentences, each carrying distinct information: the action, the paid-agent exception, and the trust caveat. The core action is front-loaded and there is no filler.

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?

No output schema exists, and the description does say the return value is the agent's answer plus, for paid agents, payment instructions. The main remaining gap is that it doesn't note the nested `arguments` object must match the callee's schema — but the schema itself covers that at 100% coverage. Adequate for an open-world proxy tool.

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 100% and every parameter is already documented, including cross-references to get_agent for the tool name and schema. The description adds no parameter-level meaning beyond what the schema states, so the baseline of 3 applies.

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: run one tool of a free MCP agent through Dolphin and return its answer. The 'free' qualifier and the note that paid agents are handled differently distinguish it from the discovery siblings like get_agent and search_agents, though the differentiation is implicit rather than named.

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?

Gives a clear exclusion rule — paid agents are not executed here, you get payment instructions instead — which is genuine routing guidance an agent would otherwise get wrong. It leaves the positive path (find tools via get_agent first) to be inferred from the schema's parameter description rather than stating it in the description.

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