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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: it performs no action itself ('opens nothing by itself') and its return payload is procedural ('screens, buttons, fields'), which tells the agent to expect instructions rather than a result. It stops short of stating prerequisites, such as whether the Bokio browser session must already be open.

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 is two useful sentences, but the third sentence is a long tangent about Bokio's REST API, price plans, private integration tokens and OAuth 2.0 registration that has no bearing on selecting or invoking this parameterless guide tool. The opening 'from ChatGPT, Claude or any AI agent' is marketing filler, and the load-bearing fact — that it does nothing but return steps — is buried mid-sentence rather than front-loaded.

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 returns, and it does so at a high level ('how to do it in Bokio step by step (screens, buttons, fields)'). However, it omits operational context an agent needs: whether a Bokio browser session must exist first, what happens if the user is not logged in, and whether the returned steps are company-specific. The API paragraph occupies space that this missing context should have filled.

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 to disambiguate and the baseline of 4 applies. The description is consistent with an argument-free call and does not invent inputs the schema lacks.

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 (a receipt in the user's Bokio account) and, crucially, corrects the misleading name by stating it 'Returns how to do it in Bokio step by step ... and opens nothing by itself' — so it is a guidance tool, not an uploader. That distinguishes it from cotlet_browser_upload and cotlet_upload_file. The opening clause 'Upload receipt in the user's own Bokio account' still echoes the title and momentarily implies a write action, which costs it a point.

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 routes the agent forward explicitly: 'then do it with the cotlet_browser_* tools in the user's Bokio Cloud Browser', which is a real when-to-use chain. But it never says when NOT to use it, nor how it relates to the obvious alternatives in the sibling list — cotlet_app_guide (a general Bokio guide) and cotlet_upload_file. The agent must infer which guidance tool to pick first.

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