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

Beyond the readOnly/idempotent annotations, it discloses return content (spoken coach lines, camera checks and non-checks), fallback behavior for unknown exercises (says so and lists close matches), and a strong behavioral guarantee that it never invents form advice. This is exactly the extra context annotations cannot carry.

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?

Four tight sentences: trigger first, then return payload, then error path, then the honesty guarantee. No filler and everything is front-loaded where an agent will read it.

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?

With no output schema, the description fully covers what comes back, what happens on unknown input, and the scope limit (bodyweight exercises). Nothing needed to call this correctly is missing.

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 100% with a single documented 'exercise' parameter, so the baseline is 3. The description's examples ('squat', 'low plank hold') mirror the schema's own examples and add no new format or constraint detail beyond 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?

States a specific verb+resource ('Get an exercise's form cues') and immediately specifies the payload: the app's real spoken coach lines plus camera checks for exercises with an Upfit page. It is clearly distinct from siblings like list_exercises and about_upfit, since it retrieves per-exercise coaching content rather than a catalog or brand info.

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 trigger: 'Use this when the user asks what Upfit's coach says or checks for a specific bodyweight exercise', with concrete example utterances. It does not contrast against list_exercises for the discovery case or state what to do when the user wants a full workout, but the invocation context is clear.

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