Retrieve employees with stable employee codes and names. Filter by name and paginate results; email appears only with PII access.
List employees. Returns employee_code (the stable id used everywhere else, e.g. for assignees), name, and non-PII fields. email is only returned if the key holds the employees:pii scope.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| search | No | Name filter |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the call read-only, and the description adds meaningful behavioral context: it returns only non-PII fields by default and only includes email when the employees:pii scope is held. This clarifies data-minimization behavior beyond the readOnlyHint and destructiveHint flags.
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 concise sentences front-load the action and then provide the most decision-relevant details: returned fields, stable ID semantics, and the PII scope requirement. There is no filler or repetition of schema content.
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 simple read-only list operation with no output schema, the description covers the return format and access prerequisites well. It does not describe pagination behavior or defaults even though a page parameter exists, and 'non-PII fields' stays vague, leaving minor ambiguity.
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 search parameter is already described in the schema as 'Name filter', but the page parameter has no description in either the schema or the tool description. The tool description adds no parameter-level meaning and only partially compensates for the schema coverage gap.
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 opens with a specific verb and resource ('List employees') and adds valuable detail about the returned identifier (employee_code) and its role as the stable ID for other operations. It is clear, though it does not explicitly contrast itself with clokio_lookup_employee or other employee-related siblings.
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 implies when to use the tool (to obtain a list of employees and stable employee codes, e.g. for assignees), but it never states when to prefer clokio_lookup_employee or when not to use this tool. The email scope caveat provides useful access context but not tool-selection guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.