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

With no annotations, the description carries the full transparency burden, and it delivers: it discloses that tools/call quotes first and may return PAYMENT_REQUIRED, that batches pay sequentially on live rails, that POST /v1/router/quote is unpaid, that the MCP does not fetch URLs, that MCP does not pay, and that GET /v1/router is free. This is unusually detailed behavioral disclosure.

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 tightly packed and front-loaded with the decisional use case, then moves into input semantics and payment behavior. It is dense but contains minimal filler; the only cost is that some clauses, like the price list in parentheses, are terse enough to require careful parsing.

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 9-parameter router with nested objects and an output schema, the description covers the essential selection and invocation context: objective handling, input restrictions, payment behavior, protocol choices, and free/introspection endpoints. Minor gaps remain for how required_output and buyer_metadata interact with routing, but the enums and output schema reduce the need for further elaboration.

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 only 56%, so the description meaningfully compensates by explaining objective aliases, top-level field folding, fg/bg aliases, and how #RRGGBB pairs in the objective become contrast inputs. Enum-based parameters like latency, evidence, and preferred_protocol remain self-explanatory, and max_price and inputs already have schema descriptions, so the overall parameter semantics are strong.

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 an explicit, specialized purpose: use this tool when you need an outcome but do not already know which zFinia utility to call. It specifies the key input ('Send objective') and aliases, and clearly positions it as a router rather than a direct utility, distinguishing it from sibling tools like accessibility_contrast_calculator.

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?

The first sentence gives a crisp when-to-use rule with an implied exclusion: if you already know the utility, you should not use this router. It also adds practical usage constraints around payment rails, quote behavior, URL fetching, and protocol options, helping an agent decide whether and how to invoke it.

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