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

Beyond the destructiveHint/readOnlyHint annotations, the description discloses atomicity, the 20-operation cap, idempotency via repeated request_id, and a 24-hour undo window. It also spells out non-obvious blast radius per kind (delete_habit removes the habit from every day, delete_task skips course/habit steps, update_course phases replace the whole list, stop_course keeps earlier days and marks).

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, then a dense but waste-free enumeration of operation kinds, each earning its clause. It is a run-on block that would scan better as a list, and minor repetition exists, but nothing is filler.

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 17-variant oneOf mutation tool with no output schema, the description covers nearly everything the agent needs to construct valid operations and understand consequences. What is missing is the failure/partial-failure contract and where to obtain the required revision (presumably get_plan or propose_changes).

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 description coverage is 0%, yet the description carries the hard semantics: date is the course start, times are dose times, phases are intake/break periods with days and dose text, and meal scope means one day / forward / all days. It also explains the dedup role of request_id and the revision requirement, compensating almost fully for the bare schema.

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?

Opens with a precise verb + resource + constraint: 'Applies up to 20 plan changes atomically', then enumerates every operation kind it accepts, so an agent knows exactly the mutation surface. Differentiation from the sibling zarok_propose_changes is only implicit (propose vs apply, and the 'requires the current plan revision' dependency), never stated by name.

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?

Clear preconditions are given (current plan revision, max 20 ops, request_id dedup), which tells the agent how to call it correctly. It does not state when to prefer it over propose_changes or what to do when the revision is stale, and no exclusions are given.

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