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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description reinforces this by saying the tool "opens nothing by itself," and it adds information beyond the annotations: it says the return value is a step-by-step guide with screens, buttons, and fields. The note that Overleaf has no public API explains why a browser-guided approach is used, which is useful context the annotations cannot convey.

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 front-loaded with the core action and its return value, followed by the execution path. The final sentence about Overleaf's official API is tangential but earns its place as justification for the browser-based workflow. The prose is dense but not padded.

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, read-only tool with no output schema and rich annotations, the description covers what the tool returns, how to act on it, and why no direct API exists. Minor gaps remain, such as what the user needs in place before compiling, but nothing essential for correct invocation 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 has zero parameters, so the baseline is 4. The description does not claim any inputs, which is consistent with the empty schema. There is nothing to document beyond the baseline.

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 makes clear that this tool does not itself compile: it "Returns how to do it in Overleaf step by step (screens, buttons, fields) and opens nothing by itself." That is a specific verb, resource, and return shape, which resolves the slight mismatch with the name "compile_project." It differentiates the tool from browser-based execution tools, but it does not distinguish the tool from sibling Overleaf tools such as overleaf_edit_file or overleaf_read_file.

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?

The description states when to use this tool: first to get the steps, and "then do it with the cotlet_browser_* tools in the user's Overleaf Cloud Browser." That routing is explicit, and the phrase "opens nothing by itself" tells the agent not to expect this tool to perform the action. There is no explicit exclusion against other Overleaf siblings, but the workflow context is clear.

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