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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: "opens nothing by itself," the shape of the return value (step-by-step screens, buttons, fields), and the absence of an official Overleaf write API. Those details tell the agent exactly what to expect back from a zero-parameter call.

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 critical fact (it returns instructions and opens nothing) appears in the second clause of the first sentence, which is good front-loading. However, "from ChatGPT, Claude or any AI agent" is pure filler, and the date-stamped API note, while relevant justification, is wordier than it needs to be. Trimming the promotional phrase would make every sentence earn its place.

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, non-destructive guidance tool with no output schema, the description supplies everything needed: what it returns, that it has no side effects, which tools to use next, and why the browser path is required. The annotations carry the safety profile, so nothing an agent needs in order to call it correctly 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?

There are no input parameters, so there is no parameter semantics to document and the baseline applies. The description does not need to explain any argument, and it implicitly frames the call as context-free aside from the user's own account.

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 action and resource (invite collaborator in the user's Overleaf account), then immediately corrects the expectation by stating it "returns how to do it in Overleaf step by step (screens, buttons, fields)" rather than performing the invite. That clarification is what distinguishes it from the cotlet_browser_* siblings. The remaining weakness is that the leading sentence reads like a mutation, so the true purpose lands one sentence late.

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 an explicit two-step workflow: call this tool for instructions, then execute with the cotlet_browser_* tools in the Overleaf Cloud Browser. The note that Overleaf has no public API explains why the browser route is the alternative. It stops short of stating any exclusion condition (for example, when to skip this and go straight to the browser), so it is clear context rather than full when/when-not guidance.

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