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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description stays consistent with them while adding real context: the call is a no-op that returns screens/buttons/fields instructions, and the actual work must be done through cotlet_browser_* in the user's DINGG Cloud Browser. The 'no public API, API keys or developer docs; built-in integrations only' note usefully explains why browser automation is required. It stops short of stating account/auth prerequisites explicitly.

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?

Front-loads the purpose, then the return behavior, then the required follow-up tools, then the API caveat — a sensible order. The dated 'checked 8 Nov 2026' sourcing note is slightly odd and the second sentence is long, but no sentence is filler.

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 params and no output schema, the description carries the burden of explaining return values, and it does ('Returns how to do it in DINGG step by step (screens, buttons, fields)'). Combined with the annotation set, an agent has enough to call it correctly and know what to do next; only explicit auth/account prerequisites are 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 takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. Schema coverage is 100% and additionalProperties is false, so no hidden inputs exist.

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?

States a specific verb and resource ('List clients in the user's own DINGG account') and names the client surfaces (ChatGPT, Claude, any AI agent). It then pivots to disclose that the tool actually returns step-by-step instructions rather than the data itself, which is a critical clarification but leaves the tool's identity slightly split between 'list' and 'guide'. It is clearly separable from the browser and booking siblings.

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?

Explicitly tells the agent what to do after calling: use the cotlet_browser_* tools in the user's DINGG Cloud Browser, and states that this tool 'opens nothing by itself'. It does not contrast against cotlet_app_guide or dingg_list_today_s_bookings, so the agent must infer when this is preferred over those, but the next-step routing is unusually concrete.

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