merit_list_vendors

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

With no annotations, the description carries the behavioral disclosure burden. It discloses that unfiltered responses can be very large, defines filter precedence, and specifies exact/partial matching and ISO date formatting. It does not describe pagination or output shape, and omits whether the endpoint is read-only — but the description's stated behavior is clear and aligned with its list/search purpose.

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?

Three sentences with no filler. The core purpose is stated first, the large-result warning is front-loaded, and the most important matching semantics are packed into the final sentence. Every sentence contributes operational guidance.

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 list/search tool with 5 optional params and no required fields, the description covers the essential selection semantics, filter precedence, scale warning, and date format. It lacks only minor operational details like pagination, sorting, and returned fields, but those would typically belong to an output schema; without one, an agent still has enough to invoke the tool 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 already 100%, so the baseline is 3. The description adds meaningful behavior beyond the schema: id wins over other filters, regNo/vatRegNo match exactly while name matches partially, and dates are ISO YYYY-MM-DD. This gives an agent matching semantics it could not infer from parameter names alone. It slightly overlaps with schema descriptions (e.g. partial/exact labels) but the precedence and date-format guidance are genuine additions.

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 names a specific verb-resource pair (list/search Merit Aktiva vendors), cites the actual endpoint, and differentiates itself from other merit_* siblings that target invoices, customers, or accounts. The no-filters-returns-all caveat further sharpens what the tool does.

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 explicitly advises preferring a filter when possible, states precedence rules (id wins over others), and distinguishes exact vs partial matching (regNo/vatRegNo exact, name partial). This gives an agent concrete criteria for selecting and tuning the call.

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