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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value beyond them: a $0.05 cost, API-key requirement, default effective-points-only behavior, and the correction-history semantics of include_superseded.

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 dense sentences with zero filler, front-loading the primary read scope before the correction behavior and cost/auth notes. Efficient and well-ordered.

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 an output schema present, annotations covering safety, and 88% param coverage, the description correctly focuses on what structured fields cannot convey (cost, auth, default filtering, correction semantics). A minor gap is the slightly ambiguous phrasing tying person subjects to condition_id rather than person_id.

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 88%, so the schema already documents nearly every parameter. The description only restates the include_superseded behavior ("returns corrections") and subject/default selection, adding marginal meaning beyond the schema's own fields.

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 ("Read private health trend points") with clear scope (self default vs person subject). It implicitly distinguishes itself from the write sibling record_health_trend via "Read", but does not explicitly name a sibling to differentiate against.

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 implied usage context: self by default, or a person subject, and points to condition_id provenance. However it offers no explicit when-not guidance and does not distinguish itself from the overlapping get_sleep/get_sleep_summary siblings despite supporting a "sleep" kind.

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