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

Annotations only declare readOnlyHint=true and openWorldHint=false. The description adds crucial behavioral detail: defaulting to 'volume' so empty calls succeed, exercise_id being required for progression/prs but ignored for volume, and the exact error case when calling progression/prs without it. This meaningfully extends the annotation signal and includes real usage data for why the default matters.

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?

The description is long but every sentence earns its place: scope, param naming, default behavior, requirement constraints, return summaries, and alternative tool routing. It is front-loaded with the core purpose and then proceeds logically, with no filler or repetition.

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 3-parameter tool with a rich output schema, the description covers parameter dependencies, default behavior, error conditions, and alternatives. The only notable gap is the lack of any explanation for date_from. That said, the output schema exists and the parameter is self-describing enough that the overall completeness is high.

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 0%, so the description carries full responsibility for parameter explanation. It thoroughly explains 'kind' (all three enum values and their semantics) and 'exercise_id' (required vs ignored contexts). However, 'date_from' appears in the schema but is never mentioned in the description, leaving its meaning entirely implicit.

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 description opens with a precise scope: 'Statistics for ONE exercise, or for training as a whole.' It clearly defines the resource and distinguishes the tool from get_coaching_context, which is the main sibling overlap. The verb is implied by the title, and the description adds specificity about the three kinds of statistics.

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?

Explicit guidance is provided throughout: 'For coaching decisions ... start from get_coaching_context instead' names the alternative and the condition for using it. It also tells the agent when to pick an exercise_id from list_exercises first, and when to default to kind='volume'. This is far beyond a vague hint.

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