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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so safety is covered structurally. The description adds genuinely new context: the tool opens nothing by itself, it returns step-by-step UI instructions, and the official API route is gated behind a Pro plan and manual approval. It does not describe how comprehensive the steps are or what happens when the customer does not exist, which keeps it from a 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 description is front-loaded with the action and the key caveat that it only returns instructions, then the follow-up tool family, then the API note. Every sentence carries information, though the API sentence is dense and includes an oddly specific 'checked 11 Oct 2026' date that reads as filler. Slight compression of the API caveat would improve it.

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 guide tool with no output schema, the description covers the essentials: what it returns, that it changes nothing, and which tools execute the real work. There is no meaningful missing information an agent would need to call it correctly.

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 and the baseline is 4. The description correctly implies a no-argument call by never referencing any inputs. No gap here, but also no added value 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 states a specific verb and resource (find a customer in the user's Setmore account) and immediately corrects the likely misreading by saying it 'returns how to do it in Setmore step by step (screens, buttons, fields) and opens nothing by itself.' That distinguishes it from the cotlet_browser_* siblings that actually perform the action. It loses a point because the name 'find_customer' implies the lookup itself is performed, so the agent must reconcile the name against the clarifying sentence.

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 clear workflow: use this to get instructions, then execute with the cotlet_browser_* tools in the user's Setmore Cloud Browser. It also rules out an alternative path by noting the official API is Pro-plan only and requires email approval from api@setmore.com. It does not explicitly say when to prefer cotlet_app_guide or how this differs from other setmore_* tools, so the routing is strong but not exhaustive.

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