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

Annotations already mark this as a non-read-only but non-destructive write, so the description's real contribution is the replacement contract: "the whole workout as it should now be, so anything left out is removed." That omission-equals-deletion behavior is exactly the kind of trait annotations cannot convey, and the note that the change appears with Undo reassures reversibility. It stops short of covering version-conflict or stale-version behavior.

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?

Two dense sentences, front-loaded with the create-or-replace contract, then the set-default rule and the undo note. Every clause carries information, with only minor density cost from packing replacement, defaults, and undo into one sentence.

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 an 11-parameter write tool with no output schema, the definition supplies the crucial mental model: full-document replacement, set-level done defaults, and undo. Given 91% schema coverage, the remaining gap is mainly what a successful call returns and how a stale version is handled, which is a modest omission rather than a blocking one.

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 91%, so the schema already explains nearly every field and this description only has to add framing. It does add genuinely useful meaning, clarifying that exercises are the full desired state and that set-level done defaults to true unless the set is planned for a later day, which is more than the schema's per-field note conveys. That pushes slightly above the baseline but not into rich parameter guidance.

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 definition gives a specific verb and resource ("Logs a new workout") and states the upsert semantics precisely: create when no id, otherwise replace an existing workout using id and version. That is clear enough for an agent to tell create from edit without inspecting the schema, though it never names a sibling such as trainrec_plan_workout to sharpen the boundary.

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?

Usage is implied rather than stated. "Sets default to done; planned sets for a later day have done: false" hints at the log-now versus plan-for-later distinction, but the definition never says when to choose save_workout over plan_workout or how it relates to edit flows. No explicit when-not conditions or alternatives appear in the text.

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