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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the safety profile is settled. The description adds real context beyond them: the return value is procedural guidance (screens, buttons, fields), the tool performs no action, and the underlying reason is that Overleaf exposes no public API for existing projects, making browser automation the only route. It does not describe the exact shape or length of the returned instructions.

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 behavioral fact (returns instructions, acts on nothing) is stated early, which is good. However, 'from ChatGPT, Claude or any AI agent' is filler, the sentences are long and run-on with semicolons, and the 'checked 5 Nov 2026' parenthetical is a distracting detail that does not help an agent decide or invoke.

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 a full annotation set and no output schema, the description supplies what an agent needs: what is returned, that no side effect occurs, and which tools to chain next. A small gap remains around what the returned guidance actually looks like and any prerequisite (e.g., an active Cloud Browser session).

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, which is the baseline-4 case; there is nothing for the description to disambiguate. It correctly implies no arguments are needed to obtain the guidance, consistent with 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 names the resource (the user's own Overleaf projects) and then clarifies the actual behavior: it returns step-by-step instructions rather than project data. The opening phrasing 'List projects in the user's own Overleaf account' reads at first like an executor, and the correction only arrives in the second sentence, which blunts the clarity slightly. It does distinguish itself from the cotlet_browser_* executors by stating it opens nothing by itself.

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 tells the agent the follow-up path: call this, then perform the steps with cotlet_browser_* tools in the user's Overleaf Cloud Browser. The 'opens nothing by itself' clause prevents the agent from expecting results from this call alone. It stops short of naming when NOT to use it (e.g., versus cotlet_app_guide or the other overleaf_* tools), so no explicit exclusion is given.

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