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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it discloses that the workout array is full-replace, that nodes kept from the read must carry their "id" and the server then preserves web-editor state, that a node without id is created new, and that the audience is only patchable under recurrence_action=one. These are the exact semantics an agent would otherwise get wrong on a destructive mutation.

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?

Four dense sentences with the workflow front-loaded before the constraints, and no filler. The parenthetical asides are long, but each carries a distinct rule (id preservation, comment fallback, confirmation threshold) rather than repeating the title.

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, deeply nested mutation with no output schema, the description covers the workflow, identity preservation, the comment escape hatch, and the confirmation gate — enough to call it safely. It stops short of describing failure modes (revision mismatch, validation rejection) that the schema documents but a quick-scanning agent might miss.

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 100%, so the schema already documents every parameter in depth, and the description's audience/recurrence_action sentence largely restates the patch schema text. The node-id preservation guidance is genuinely useful but also echoed in the schema's id fields, so this dimension lands at the baseline rather than above it.

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 opening sentence states a specific verb and resource ("Update a planned training workout") and immediately establishes the read-modify-write pattern. It does not explicitly differentiate itself from near-name siblings such as update_planned_event or create_planned_training, so an agent must infer the boundary from the resource noun alone.

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?

Explicitly names the prerequisite tool ("Read it first with get_planned_training"), the intermediate step ("apply your changes in reasoning"), and the fallback for unrepresentable intent ("put it in the comment of the relevant node — never approximate it"). It also defines a concrete escalation rule: more than 3 write operations requires listing computed dates/targets and getting explicit confirmation.

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