Set plan

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds behavior the annotations do not: it emits a warning when no item is on a hard lever, and items that remain 'keep their done state.' That is genuine behavioral disclosure beyond structured fields.

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 core action ('Replace the plan for a day') followed by the key invariant and edge-case notes. Four short sentences, no filler. The 'Other items: paid work, family, workout, etc. with their area' clause is slightly telegraphic but earns its place by mapping examples to the area field.

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 destructive, idempotent mutation with no output schema, the description covers the critical domain invariant (single main step), warning behavior, and done-state retention, with safety carried by annotations. Gaps remain around how date defaults and the unused optional fields, but nothing essential to a correct call 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 50%, and the description compensates by explaining isMainStep (exactly one must be true), the provenance of stepId (from next_steps), the hard-lever linkage for leverId, and the intent of area (paid work, family, workout, etc.). It leaves projectId, estimateMin, and the date format undocumented, so it is helpful but not exhaustive.

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 and resource with scope: 'Replace the plan for a day.' This implicitly separates it from item-level siblings like edit_plan_item and delete_plan_item (whole-plan replacement vs single-item edit). It does not name any sibling explicitly, so it falls short of full differentiation.

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 content rules for a valid call (exactly one isMainStep=true, ideally linked via stepId from next_steps, on a hard lever) rather than guidance on when to call this versus edit_plan_item, delete_plan_item, or add_steps. Usage is implied by 'Replace the plan for a day' but no when-not conditions or alternatives are stated.

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