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

With annotations present, the description adds substantial behavior the annotations don't cover: exact cost (1.00 USDC on Base), a 10-call shared 30-day free allowance, required credentials/mandates/action grants, and the explicit statement that the adapter 'grants no authority and never supplies server credentials.' It also implies why readOnlyHint=false for what is otherwise a pure computation — the call is billed. It stops short of describing error behavior or what happens when limits are exceeded.

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 core purpose is buried behind a leading pricing sentence, and the price is stated three separate times ('1.00 USDC per call', 'Direct runs cost 1 USDC', 'the Labs MCP and resolver computation paths are free' repeated). The free-path information appears twice and the legal boilerplate ('grants no authority', 'bounded computation on caller-supplied data') pads the tail. The purpose sentence should lead.

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?

There is no output schema, so the description must state the return shape — it does: matched and missing items. For a two-parameter bounded computation, it covers cost, auth, input roles, and output shape. The gaps are minor: no error/limit-exceeded behavior and no hint about result ordering or deduplication beyond what the item schema says.

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 0% at the property level, so the description has to carry parameter meaning. It does map the two inputs to roles ('required list' vs 'available evidence labels') and names the outputs, which is genuine value beyond the schema. However, it never mentions the concrete constraints (16 items max, 96-byte unique ASCII labels) or which parameter is which by name, so an agent still has to open the 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 second sentence gives a specific verb and resource: 'Compare submitted evidence labels with the required list and return matched and missing items.' That is a precise description of a set-difference computation. It does not name a specific sibling tool, but it does point to the free '/api/mcp or /api/service-resolver' paths, which is enough to distinguish this paid adapter from the free computation routes.

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 'Operating boundary' block states when to use it — supply required and available labels, read matched/missing, agent requests missing items, human reviews documents — and the pricing text steers callers to the free computation paths instead. What is missing is an explicit rule for when the paid path is mandatory versus merely convenient, but the conditions given are clear and actionable.

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