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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, non-destructive), so the bar is lower. The description nonetheless adds real behavioral context the annotations don't: the operation is scoped to the signed-in user and it fails when a fast is already active. It omits the failure mode details (error shape) and whether a template/goal is applied.

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?

Two short sentences with no waste; the default behavior is front-loaded and the precondition follows. Every clause carries information.

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 one-optional-parameter mutation with full schema coverage, existing annotations, and no output schema, the definition covers what an agent needs to call it correctly: what it does, scope, and the key precondition failure.

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?

Schema coverage is 100%, so the single 'at' parameter is already fully documented as an ISO 8601 timestamp defaulting to now. The description's '(or at the given time)' only mirrors that, adding no syntax or format guidance beyond the schema, so baseline 3 applies.

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 ('Start a fast') plus the scope ('for the signed-in user'), which cleanly distinguishes it from the still_end_fast and still_get_fasting_state siblings. It does not explicitly name those alternatives, so sibling differentiation is implicit rather than stated.

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?

'Fails if a fast is already running' implies the caller should verify state first, but no explicit guidance is given about checking still_get_fasting_state or choosing a template via still_select_fasting_template before starting. Usage is inferable but not spelled out.

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