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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the description is not required to establish that this mutates state. It still adds real behavioral detail beyond them: planning onto an empty day causes 'the week opens around it' (side effect on surrounding days), and a non-matching title fails while returning the available dishes to choose from. It does not say whether the shopping list or ingredient plan is recalculated, which is a meaningful gap for a meal-planning tool.

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?

Three short sentences, front-loaded with the core action and the matching rule, with no filler. The clause 'on a day nobody has planned yet too: the week opens around it' is slightly convoluted and would read better as a separate sentence, but nothing is redundant.

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?

With only two parameters and no output schema, the description covers what an agent needs to call it correctly: the target date, the title source, exact-match requirement, unplanned-day behavior, and the failure mode. The only missing piece is downstream effects on shopping/ingredients, which matters but is not required to invoke the tool.

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 baseline is 3, but the description genuinely adds semantics: the title must be an exact match, and it may resolve either against the day's suggestions or the household recipe library. That constrains the free-text `dishTitle` beyond the schema's looser 'one of the day's suggestions, or a recipe in the library'.

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: 'Swap the planned dinner on a date to another dish... by its title', and clarifies the two valid title sources (the day's suggestions or a library recipe). It is clearly distinguishable from plan_week or replan_open_days, though it never names a sibling explicitly.

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 conditions for use: the dish must be one of that day's suggestions or an exact library recipe title, and it works both on planned and not-yet-planned days. It does not state when to prefer alternatives such as mark_eating_out, wish_dish, or replan_open_days, so there are no explicit exclusions.

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