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

Annotations already declare destructiveHint=true and idempotentHint=true; the description earns credit by explaining why: planned entries cause the call to report a count instead of writing, and discardPlanned=true actually drops them. It also discloses the self-healing behavior (eating into the slot removes the skip) and the downstream effect on day evaluation. It does not spell out the success response shape, which keeps it short of 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?

Front-loaded with the action and scope, then behavior, then the exclusion. Every sentence carries information, though the nested parenthetical enumerating slot names alongside the clarification is slightly dense and mixes German and English inline.

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 4-parameter mutation with no output schema, the description covers the two things an agent could not infer: that the call may refuse to write and instead return a count, and that the skip is later removable by ordinary logging. Nothing needed to call it correctly is missing.

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 baseline is 3; the description adds real meaning by pinning 'label' to a time slot rather than a saved dish, and by framing discardPlanned as the switch that converts a no-op into a destructive drop of planned entries. tz and date are left entirely to the schema, which is adequate given their clear descriptions.

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?

Uses a specific verb and scope ('Declare a meal slot ... as skipped for one day') and disambiguates the resource twice: the slot is 'the time slot, not a saved dish' and 'This is not fasting: fasting windows are kept in Still.' That cleanly separates it from joiva_plan_food/joiva_log_meal and from the still_* fasting tools without opening any schema.

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 the triggering scenario ('Mittagessen fällt heute aus') and an explicit when-not with the alternative system ('This is not fasting ... kept in Still'). It also states that consuming the slot later auto-clears the skip. The only gap is that joiva_unskip_meal, the obvious counterpart, is never named as the manual undo path.

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