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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description goes further by disclosing that auth mode changes both the source (Internal API vs. curated guest set) and the result cap (8 vs. 6), and that guest results carry an embedDemoUrl. It also flags the Bearer-token-only constraint, which is real operational context not present in the annotations. Only error/fallback behavior when OAuth is present but the team has no workouts is left unstated.

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 the primary outcome, then auth-mode behavior, then use cases, then exclusions — a good information hierarchy. Dense but every sentence carries routing or behavioral signal; the parenthetical about Bearer tokens is the only slightly awkward insertion.

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 shape needn't be explained, and the two-mode behavior is well covered. But with five optional filters at 0% schema coverage, an agent has no idea from this description what filtering is possible or whether the filters are ignored for guest samples — a meaningful gap for a list tool with that many knobs.

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 the description never mentions any of the five filters — locale, difficulty, category_id, duration_min, duration_max — nor whether they apply to guest samples at all. The only constraint documented anywhere (duration_min <= duration_max) lives in the schema's top-level description, not here. For a 0%-coverage schema, the description should be carrying this burden and does not.

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 ('Returns a workout carousel for sample-workout prompts') and immediately splits the behavior into two concrete modes: OAuth-connected team workouts vs. unconnected guest samples. The final sentence names the sibling tools it is not, so an agent can distinguish it from list_team_workouts without opening either 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?

Explicit positive triggers ('when the user asks for sample workouts, a workout carousel, or embed demo preview') and explicit negative routing with the correct alternatives for each case: list_team_workouts for full team-library views, get_integration_plan for plans, get_embed_code_samples for copy-paste HTML. Nothing is left to inference.

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