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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, but the description adds the genuinely surprising disclosure that the tool "opens nothing by itself" and only returns procedural guidance (screens, buttons, fields). That is exactly the behavioral context an agent needs to avoid assuming it will fetch data. The API/MCP-server trivia is noise, but the key behavioral trait is disclosed.

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?

The description is compact. It front-loads what the tool returns and then states the next step and that the tool performs no action. The marketing phrase ("from ChatGPT, Claude or any AI agent") and the API availability note are minor waste but do not block understanding.

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 zero-parameter guidance tool with no output schema, the description covers what is returned (step-by-step screens, buttons, fields) and how to proceed afterward. Only the naming ambiguity around whether actual holiday data is returned remains unresolved.

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 no parameter semantics to explain and the baseline is 4. The description adds nothing that contradicts or complicates the empty schema.

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 explains the mechanism well: it returns step-by-step instructions for listing holiday requests in PeopleHR rather than the data itself. However, this directly conflicts with the tool name and title "List holiday requests," so an agent skimming names could reasonably expect returned records. The core verb/resource is present, but the actual payload is only clarified after reading a long sentence.

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 does tell the agent what to do next: use the cotlet_browser_* tools in the PeopleHR Cloud Browser, which is genuinely useful follow-up guidance. It gives no guidance on when to pick this over siblings such as peoplehr_get_employee_planner or peoplehr_list_employees, nor any when-not conditions.

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