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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the non-obvious core behavior: this returns a procedural walkthrough and performs no browser action itself, so the agent knows it must follow up with browser tools. The note about CharlieHR's narrow API and lack of an official MCP server explains why browser automation is required, adding useful context the annotations cannot carry.

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 core mechanic is front-loaded, which is good, but 'from ChatGPT, Claude or any AI agent' is promotional filler and the closing API sentence is repetitive ('CharlieHR's official API: CharlieHR has an API, but a narrow one'). Roughly a third of the text could be cut without losing instruction value.

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 parameterless, read-only guide tool with no output schema, the description covers what the output contains (screens, buttons, fields), what it does not do (open anything), and the required next step (cotlet_browser_*). Only the precise shape of the returned instructions and whether they must be followed verbatim is left unstated.

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 and the schema is a closed empty object, so there is no parameter meaning to add. Baseline 4 applies; the description correctly implies no inputs are needed by describing an account-scoped guide lookup.

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 and resource (list team members) and immediately clarifies the actual mechanic: it returns step-by-step instructions (screens, buttons, fields) rather than data. This resolves the ambiguity that the name alone would create, though the phrasing 'List team members ... Returns how to do it' is initially jarring.

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 says the tool 'opens nothing by itself' and instructs the agent to then execute with cotlet_browser_* tools in the user's CharlieHR Cloud Browser, which is actionable routing. It does not, however, contrast itself against cotlet_app_guide or say when a pure guide lookup is preferable to skipping straight to the browser.

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