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

Beyond the readOnlyHint and destructiveHint annotations, the description reveals critical behavioral traits: it requires explicit user consent, restricts inputs to non-identifying user-authored notes, and mandates that output be phrased as questions rather than causal assertions. These are important privacy and safety behaviors that are not captured in annotations.

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?

The description is compact, with two sentences that front-load the consent prerequisite, then clearly convey the main action and the output framing. No words are wasted, and each sentence earns its place by adding critical operational or safety information.

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?

Given the tool has five parameters and an output schema, the description covers the core semantics, consent requirement, PHI restriction, and output style. It does not detail the return structure, but the output schema is available to fill that gap. It lacks explicit mention of alternative tools, but the purpose is clear enough, and the annotations and schema complete the picture.

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?

The schema description coverage is low (only consentConfirmed has a description), but the tool description compensates by labeling 'before, during, and after observations' which maps directly to baselineBefore, during, and recoveryAfter parameters, and 'suspected patterns' maps to possiblePatterns. It does not provide per-parameter examples or format details, but the semantic grouping is sufficient for an agent to infer parameter purposes.

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 clearly states the tool's function: it structures non-identifying, user-authored before/during/after observations and transforms suspected patterns into questions. The verb 'structure' and 'turn' with specific objects distinguishes it from sibling tools like 'build_health_timeline' or 'prepare_appointment_brief', which focus on timeline construction or brief preparation.

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 description explicitly states a prerequisite ('After explicit consent') and a strict constraint ('Do not accept PHI'), which tells the agent when it is appropriate to use. It also instructs to frame patterns as questions rather than causal claims, providing a clear usage behavior. However, it does not explicitly name alternative tools or state when not to use it, though the purpose clarity indirectly provides this.

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