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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value on top: it explicitly says it 'opens nothing by itself' and that the return value is procedural step-by-step screens/buttons/fields rather than data, plus notes that Deputy has a REST API but no official MCP server. That is context an agent cannot get from the annotations alone.

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 value — that it returns step-by-step instructions and performs no action, then hands off to cotlet_browser_* — is buried in the middle of the second sentence. The framing 'from ChatGPT, Claude or any AI agent' and the trailing API/MCP trivia ('checked 20 Oct 2026') are filler that competes with the actionable content.

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 guidance tool with no output schema, the description covers what is returned, that no side effects occur, and what to do next. What it does not address is scope — whether the steps are generic or account-specific, and whether any authentication or active Deputy session in the browser is required before the browser tools will work.

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 nothing for the description to disambiguate; the baseline for a no-parameter schema applies. No misleading hints about inputs are given.

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 does state a specific resource (leave requests in Deputy), but it opens as if the tool retrieves that data and only later reveals it actually 'Returns how to do it in Deputy step by step (screens, buttons, fields)'. That reframe is the real purpose, and stating it second rather than first leaves an agent briefly unsure whether this returns records or procedural guidance. Nothing distinguishes it from the approve/decline leave siblings, which presumably follow the same guide pattern.

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 a concrete next step — perform the task 'with the cotlet_browser_* tools in the user's Deputy Cloud Browser' — which is genuine routing guidance. However, there is no statement of when this tool should be preferred over the sibling deputy_approve_leave_request or deputy_decline_leave_request, and no prerequisites or exclusions are given.

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