get_examples

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

With no annotations, the description must carry the behavioral load; it does disclose a meaningful trait beyond the schema — that some returned items carry an OLD STYLE flag and are unsuitable as templates. It says nothing about ordering, whether results are truncated by the limit, or the read-only nature of the call, leaving those to inference.

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 short sentences with the positive definition first and the OLD STYLE warning second — no filler. The wording is slightly compressed ('coach text + the steps the athlete built') but still readable.

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?

An output schema exists, so return values need no explanation, and the description covers what the tool returns conceptually. However, for a tool whose two numeric parameters are entirely undocumented, the definition is not fully sufficient to tune the call correctly.

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 0% and neither 'limit' nor 'days_back' is mentioned in the description, so their defaults (8 and 180) and effect are undocumented anywhere. The phrase 'recent workouts' only loosely gestures at a time window without clarifying that days_back controls 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 description names the resource ('recent workouts that already have a structured workout') and the payload ('coach text + the steps the athlete built'), which is specific enough to distinguish it from list_workouts or get_structured_workout. It never states an explicit verb ('return', 'fetch'), so the agent infers retrieval from the 'get_examples' name rather than the prose.

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?

The only directive is a data-quality caveat — entries flagged OLD STYLE 'must not be copied' — which tells the agent how to use the results but not when to pick this tool over siblings like list_workouts or get_structured_workout. The purpose (gathering reference examples) is implied rather than stated as a usage condition.

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