preview_structured_workout

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

With no annotations, the description carries the safety burden, and it does the most important part by stating 'Writes nothing' and framing the tool as a validation gate against 'hard rules'. It leaves some behavior implicit: it never says what a rule violation looks like (error text vs. partial preview) or that the preview_token is scoped/expiring. Strong but not complete for a zero-annotation tool.

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?

Front-loaded with purpose and the no-write guarantee, then the step grammar, then the follow-up action — a sensible order with no filler sentences. The brace/bracket notation is dense and telegraphic, which is efficient for a model but slightly harder to parse than plain prose.

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 2-parameter validation tool with no annotations and no output schema, the description covers the input contract, the prerequisite read, and the downstream save handoff. Gaps remain around the response shape (what preview text looks like, whether preview_token is returned always) and error behavior on rule violations, which matter because there is no output schema to fall back on.

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% and 'steps' is an untyped free-form object array, so the description's inline grammar (kind enum, exactly one of distance_km|distance_m|minutes|seconds|time, exactly one target, optional English note, repeat nesting) supplies nearly all the meaning an agent needs to build valid input. The 'name' parameter is never mentioned, and the grammar arguably duplicates get_parsing_rules, keeping it short of a 5.

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 ('Check compact steps against the hard rules and render a preview') and immediately scopes it against the write path with 'Writes nothing' plus the handoff to save_structured_workout. An agent can tell this apart from save_structured_workout or get_structured_workout without opening any schema.

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 prerequisite ('Read get_parsing_rules first'), an explicit ordering rule ('Show the text to the athlete; pass preview_token to save_structured_workout after the athlete approves'), and thereby names the alternative tool and the condition that selects it. This is a full workflow contract, not a hint.

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