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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the return value is a procedure, not data, and execution requires a separate browser tool family in the user's own session.

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 opening two sentences are front-loaded and efficient. The trailing paragraph quoting Exercise.com's paid API pricing is tangential to invoking this tool and reads as boilerplate that dilutes the core instruction.

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-param, no-output-schema tool, the description covers what it returns and what the agent must do next. The only missing piece is how the specific client/account context is established.

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, but the description never addresses how a target client is identified with no arguments at all — an agent must infer targeting from the browser session context. That is a real semantic gap for a zero-param tool.

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+resource ("View client nutrition") and, crucially, clarifies that the tool returns a step-by-step procedure ("screens, buttons, fields") rather than the nutrition data itself. It does not differentiate itself from the many exercise_com_* siblings, but the read-and-guide nature is unambiguous.

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?

Gives an explicit workflow: call this to get instructions, then execute them with the cotlet_browser_* tools in the Cloud Browser. "Opens nothing by itself" sets a clear boundary on what happens after invocation. It lacks when-not guidance or references to alternative exercise_com_* view tools.

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