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

Annotations already declare readOnlyHint=true, destructiveHint=false, and a closed domain, so safety is covered. The description adds genuine behavioral value by disclosing the returned fields (status) and, importantly, that IDs are cross-tool handles for run_employee and get_employee_run. Return format and ordering are not described, but that is minor given no output schema and no parameters.

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 short sentences, no waste: the first states what comes back, the second states what to do with it. What the tool returns is front-loaded ahead of the follow-up routing advice.

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 no parameters and no output schema, an agent needs only to know what the list contains and how the returned IDs are consumed. The description supplies both, plus the fact that status is included, so nothing material 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool is 4. The description correctly implies the call is unfiltered within the caller's organisation.

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 identifies the resource precisely ('The AI employees you can use in your organisation, with their status') and implicitly distinguishes itself from run_employee and get_employee_run, which it names as consumers of its output IDs. It lacks an explicit listing verb ('list all'), but the resource and scope are unambiguous.

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 gives clear forward guidance: take an id from this result and pass it to run_employee or get_employee_run. That establishes the discovery-then-act workflow and implicitly tells the agent to call this first. It stops short of stating when not to use it or how it relates to other list_* siblings.

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