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

With no annotations provided, the description carries the full burden. "GET" implies a safe read and "Explicit company required" flags a hard constraint, and "Flat query fields" hints at query shape, but there is nothing about auth scope, pagination, rate limits, or what "policies" actually contains. For an unannotated tool this is well short of adequate disclosure.

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 terse fragments, front-loaded and low on waste. But "Fixed JSON" is undefined jargon that consumes space without conveying meaning, and the sentence fragments stop short of a complete statement of behavior.

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 required-company constraint is covered. Still, for a tool with a completely opaque `query` parameter and no annotations, the definition never says what payroll policies are or what the response represents, which is not enough for an agent to call it with confidence.

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 0%, so both parameters are undocumented in the schema — `query` is an opaque anyOf object with additionalProperties:true. The description compensates partially by stating company_name must be explicit and that query takes flat fields with filters discoverable via describe_nextesy_operation, but it lists no field names or types, leaving the agent dependent on a second tool call.

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 the endpoint (GET /api/v1/payroll/policies), from which an agent can infer it retrieves payroll policies, but it frames the purpose in HTTP mechanics ("Fixed JSON GET") rather than business semantics. It offers no differentiation from close siblings such as get_payroll_configuration, get_payroll_company, or list_payroll_periods, so the agent must guess which payroll resource it actually needs.

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?

"Explicit company required" gives a precondition, and "see describe_nextesy_operation for filters" is a genuine routing hint that tells the agent where to go for query construction. However, there is no statement of when to call this tool versus overlapping siblings like get_payroll_configuration, so the usage guidance is implied rather than stated.

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