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

With no annotations, the description carries the full behavioral burden, and it does disclose meaningful context: the tool is free, payment settles on Base L2, the phone number is revealed only after settlement, and there is a 1% rail fee. However, it describes the underlying service rather than the tool's own behavior — it says nothing about whether invoking it costs anything, latency, or rate limits.

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 value proposition is front-loaded and the payment mechanics earn their place, but a large block of raw endpoint URLs and promotional phrasing ('We move the money, not the voice') inflates the text without clarifying the tool's own contract.

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?

An output schema exists, so return values need no explanation, and the ecosystem context is rich. What is missing is the tool's own contract: whether it returns the directory or a single business's details, and how the lone parameter changes that — leaving a gap for a tool that is otherwise simple.

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?

The single 'business' parameter has 0% schema description coverage, so the description must compensate. It only indirectly implies semantics via the sample POST body {"business": "<slug>"}, without stating that the parameter is a business slug, whether it is required, or what happens when it is omitted (it is not required, per schema).

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 explains the Pay-to-Call service and its economics clearly, but it reads as marketing copy for the ecosystem rather than stating what THIS tool does — a directory fetch, a business lookup, or a general info dump. The presence of an undocumented 'business' parameter hints at a lookup, yet the text never resolves it, and nothing distinguishes it from the many sibling *_info tools (settlement_rail_info, diav_info, eds_info).

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?

No when-to-use or when-not-to-use guidance is given. The endpoint list implies possible flows (browse directory, start a call, register), but the description never says which flow this tool triggers or how it relates to siblings, leaving the agent to guess.

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