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

Annotations flag destructiveHint=true and readOnlyHint=false, and the description correctly reinforces that instead of contradicting it, adding that kept nodes retain their id and that the server preserves web-editor settings on them. The id-omission-equals-new-node rule is real behavioral disclosure the annotations cannot carry. It stops short of stating what happens to nodes dropped from the re-emitted array.

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 sentences, purpose front-loaded, then workflow, then the id rule, then two guardrails. Every sentence carries either a procedure or a constraint, and nothing repeats the schema verbatim.

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 mutation tool with a very deep nested schema and no output schema, the description covers the parts that matter operationally: read-first, id preservation, the comment escape hatch for intent the schema cannot express, and a confirmation gate for large writes. Required category, revision token and full-replace semantics of `workout` are all carried by the schema.

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 all three parameters and the deep nested node types are already documented in the schema — baseline 3 applies. The description adds one genuinely useful overlay (id preservation vs. new-node creation, which the schema also repeats per node type) but no additional semantics beyond that.

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 — "Update a library workout template" — which separates it from create_training_frame and list_training_frames. It also names get_training_frame as the mandated read step, but never distinguishes itself from apply_training_frame or update_planned_training, so an agent must infer which update path applies.

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 an explicit read-modify-write sequence: read with get_training_frame, compute changes in reasoning, then send the patch. Also adds a threshold rule (more than 3 write operations requires listing computed dates/targets and getting confirmation). No stated when-not or alternative-tool routing.

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