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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true — they say nothing about partial-update semantics. The description adds genuinely non-obvious behavior: omitted fields are preserved and sending exercises replaces the entire exercise list. That is exactly the kind of context the annotations cannot convey, though it stops short of stating permission requirements or what a partial-vs-full replacement returns.

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, zero filler, with the core edit semantics and the most dangerous side effect (exercises replacement) front-loaded before the partial-update rule. Nothing repeats what the schema or annotations already state.

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?

It covers the highest-risk behavior (list replacement) and the patch model, which are the essentials for a 12-parameter mutation with no output schema. It still leaves most editable fields undocumented at a 17% schema coverage level and omits any mention of authorization or what happens if workoutId is unknown.

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 very low (17%) across 12 parameters, so the description carries the burden — but it names only about five fields, in non-matching terminology, and says nothing about status, category, week_name, warmup_notes, cooldown_notes, or estimated_minutes units. The one strong addition is the replace-whole-list semantics for exercises, which clarifies a nested array the schema leaves undescribed.

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?

Names a specific verb and resource ("Changes a workout") and enumerates the editable facets, so the agent knows it is an edit rather than a create/publish. However, the field list is stated in loose synonyms ("name, notes, day, length") that don't match the actual schema keys (title, description, day_of_week, estimated_minutes), and it omits status, category, week_name and the note fields entirely.

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?

"Send only what changes" plus the warning about exercises replacement gives real operational guidance for invoking it correctly. But it never says when to use this over siblings like create_workout, publish_workout, or set_workout_weeks, so the alternative-selection guidance is only implied.

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