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

The readOnlyHint/idempotentHint/non-destructive annotations are corroborated by 'opens nothing by itself', so there is no contradiction and the description adds the useful framing that the output is procedural rather than executable. It also scopes the tool to the user's own account. It does not state prerequisites (logged-in browser session, plan tier) or rate limits, so a 4 rather than 5.

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 first two sentences are front-loaded and earn their place, but the trailing API paragraph is tangential — it explains why an API route isn't available rather than how to call this tool — and includes a specific verification date that adds noise. Roughly a third of the text could be cut without losing call-relevant information.

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?

With no output schema, the description does carry the burden of explaining the return: a step-by-step procedure with screens, buttons, and fields. That is adequate but thin — it doesn't say whether the guide is static or account-specific, or how to hand off from the returned steps to a specific cotlet_browser_* call, which is the main complexity an agent must manage here.

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 the baseline is 4 and there is no parameter meaning the description needs to carry. Nothing here misdescribes or invents inputs.

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 states a concrete outcome: it returns ZenMaid's assign-cleaner procedure step by step (screens, buttons, fields) and explicitly says it performs no action itself. This resolves the ambiguity created by the name 'assign_cleaner', which would otherwise suggest a write operation. It falls short of 5 because the name and the actual behavior are in tension, and the agent has to read the full description to learn the tool is a guide, not an executor.

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 sequencing rule: get the steps here, then execute them with the cotlet_browser_* tools in the user's Cloud Browser. That is real when-to-use routing rather than inference. It does not, however, distinguish this from the sibling cotlet_app_guide, nor say what to do if the user lacks a ZenMaid account or an active browser session.

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