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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and the description is consistent with them by stating it opens nothing and only returns instructions. Beyond that it adds the API-approval context and the handoff to browser tools. It does not describe the shape or length of the returned instructions, which matters for a guidance-only tool with no output schema.

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?

It is short and front-loads the outcome and the no-side-effect guarantee. The middle clause ('Returns how to do it in Markate step by step (screens, buttons, fields) and opens nothing by itself') is slightly tangled, and the dated API-approval parenthetical is dense, but nothing is redundant.

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, no-output-schema tool, the description covers what is returned (step-by-step screens/buttons/fields) and what the agent must do next with cotlet_browser_*. It could say more about how detailed or paginated the instructions are, but an agent has enough to invoke 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 the schema carries the full burden and there is nothing for the description to disambiguate. Baseline of 4 applies; no parameter detail is required or missing.

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 makes the real function clear: it generates step-by-step Markate UI instructions (screens, buttons, fields) rather than performing the creation itself, and explicitly says it 'opens nothing by itself'. That corrects the misleading 'create' verb in the name. It does not contrast itself with the markate_* siblings (e.g., markate_create_invoice), so sibling differentiation is only partial.

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 states the workflow explicitly: call this first, then execute the steps with the cotlet_browser_* tools in the user's Markate Cloud Browser. It also explains why this path exists (the official API key requires an approval form). It gives no explicit 'when not to use' or exclusion against alternative paths beyond that API note.

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