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

With no annotations, the description carries the full burden and does substantial work: it discloses that tools/call quotes first and can return PAYMENT_REQUIRED at an unchanged price, lists price points for known live resources, notes batches are sequential pays, and states 'MCP does not pay' and 'No URL fetching'. The pricing parenthetical is cryptic, and it never says what a successful (non-PAYMENT_REQUIRED) response contains, so it stops short of 5.

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?

It is front-loaded with the when-to-use condition, which is good, but the 'contrast 1000, DCC 3000, catalog-offer 100000, changes-since 10000' parenthetical is dense jargon that costs more parsing than it returns. The prose is compressed to the point that some sentences do not clearly earn their place.

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 paid router with no annotations and no output schema, the description covers the payment model and input folding well. But it leaves the enum tuning parameters undefined and only gestures at the response shape via an external contract URL, so an agent still has gaps before invoking it 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 coverage is 56%, and the description adds real semantics: objective aliases (goal/task/outcome/query), top-level colour/field/html/cursor keys folding into inputs, fg/bg aliasing, and #RRGGBB extraction from the objective. However, none of the four enum parameters (latency, evidence, freshness, preferred_protocol) are explained anywhere, leaving meaningful gaps.

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 frames the tool as a dispatcher: 'Use when you need an outcome and do not already know which zFinia utility to call', which tells an agent this is the generic entry point versus the concrete siblings. The verb is only implied ('Send objective ... plus inputs'), and 'outcome' remains abstract, so it is clear but not maximally sharp.

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 states an explicit selection condition — use it when you don't know which utility to call — which implicitly routes agents to concrete siblings when they do know. It also separates paid paths (tools/call) from the unpaid quote endpoint (POST /v1/router/quote) and the free contract (GET /v1/router). No explicit exclusions are named, keeping it at 4.

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