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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds the single most important behavioral fact: this call does not apply the change, it only returns screens/buttons/fields instructions and 'opens nothing by itself', requiring a follow-up in the Cloud Browser. It also explains why that pattern exists (no public CoachingPortal API), which prevents an agent from falsely reporting success.

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 constraint is front-loaded in the first two sentences and every sentence carries information. The middle sentence is a semicolon-chained run-on ('...opens nothing by itself; then do it with the cotlet_browser_* tools...'), which costs a little readability but no substance.

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 tool with no output schema, the description covers what matters: what is returned (step-by-step screens/buttons/fields), that nothing is executed, and the required follow-up tool family. It does not specify which calculation defaults exist (macros, targets, rounding), though the returned instructions would presumably resolve that at call time.

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 and there is nothing further for the description to disambiguate. No parameter meaning is lost.

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 a specific verb and resource - 'Set calculation defaults in the user's own CoachingPortal account' - and scopes it to the user's own account rather than a client's. It is weaker on sibling differentiation: many siblings (set_adherence_weights, set_weight_tracking_policy, set_workspace_units) are also single-setting mutations, and the description never says which calculation defaults this covers or why it is distinct from those.

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 clear operative guidance: the call returns step-by-step instructions and changes nothing itself, so the agent must then act via the cotlet_browser_* tools. That workflow is unambiguous. The gap is exclusions - no statement of when to prefer a sibling setter tool instead of this instruction-returning pattern.

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