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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description adds the valuable constraint that the call must be gated on an explicit user decision. However, it frames 'stop tracking' purely as recording a decision, while the optOut parameter actually deletes all stored data for the user — a consequential effect the description leaves entirely unstated, which sits awkwardly with destructiveHint=false.

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 sentences, front-loaded with the trigger condition, then the stored effect, then the negative constraints. Nothing is padding; even the repeated 'never' clause adds a distinct failure mode to avoid.

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 three-boolean tool with no output schema, the description covers the invocation conditions, the two consent scopes, and the consent-gating rule. The remaining gap is the consequence of opting out (data deletion) and any indication of the response, which is minor but not trivial for a privacy tool.

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 100%, so the schema already documents all three booleans, and baseline is 3. The description does add meaning by clarifying that the two consent decisions are stored separately, but it never mentions optOut, the highest-risk parameter, so it adds little on the parameter front beyond what the schema already says.

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 a specific verb and resource (stores the consent decision) and splits it into two clearly scoped consents: derived performance scores and a coaching-contact record. That is enough to separate it from plan-building siblings like fitness.build_fuel_plan, though it never explicitly distinguishes itself from fitness.submit_coaching_interest, which is the nearest neighbor for the coaching-contact half.

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?

It gives three concrete when-to-use triggers (user asks what is stored, agrees to tracking, asks to stop tracking) and two explicit when-not rules (never proactively, never as an end-of-conversation default prompt). That is about as much routing guidance as a consent tool can carry.

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