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

readOnlyHint already declares this is a safe read, and the description adds genuinely new behavior: the hard one-filter minimum, why it exists (no full-list reply), and the underlying POST /api/v1/getcustomers call. It does not mention result cap behavior beyond what max_results already documents.

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?

Two tight sentences with the filter semantics front-loaded and the hard constraint immediately after; the endpoint is a compact trailing detail. No filler or restatement of the title.

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?

With readOnlyHint covering safety, 100% schema coverage on all six parameters, and no output schema to explain, the description supplies the one thing the schema omits: the mandate that a filter be provided. Nothing needed to call this correctly is missing.

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% so the baseline is 3, but the description adds meaning the schema does not: which keys match partially versus exactly, and that at least one of them must be supplied (the schema marks zero required parameters). That materially improves correct invocation.

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 (search) and resource (customers) plus the exact searchable keys and their match semantics (partial name, exact registry/VAT number, id, changed_since). An agent can separate this from merit_list_vendors or merit_create_customer without opening any schema.

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?

Explicitly states the gating condition: at least one filter is required because Merit cannot return the whole customer list in one reply. That is real when-to-use guidance, though it names no alternative tool for the cases it excludes (e.g. where to go for vendor searches or full exports).

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