anomalies

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

With no annotations, the description carries the full behavioral burden, and it does so for the important part: it defines the detection semantics (single-day outliers vs. streaks of 5+ consecutive days relative to a baseline average) and notes streaks can fire even when no single day is an outlier. It omits operational traits such as whether results are computed live or cached, and any sensitivity/threshold configurability, which keeps it short of a 5.

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 purpose, then output taxonomy in a single follow-on sentence with no filler. The parenthetical streak definition is dense but earns its place by teaching the agent a non-obvious detection rule.

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?

There is no output schema and no annotations, so the description's explanation of the two finding kinds is genuinely necessary and good. However, the three required parameters remain completely unspecified (field naming and date format), which an agent needs in order to call the tool correctly.

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 all three parameters (field, date_from, date_to) are undocumented. The description only obliquely implies field is 'one health field' and says nothing about date_from/date_to format or range semantics, so it only partially compensates for the coverage gap.

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 object ('Find days where one health field broke from its own recent pattern') and immediately distinguishes itself from detection-adjacent siblings like baselines, gaps, and correlate by naming the two finding types it produces. An agent can tell what this tool returns without opening the 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?

Usage is implied rather than stated: the outlier/streak examples show when the tool is useful ('catching a slow drift, e.g. a gradually rising resting heart rate'), but there is no explicit when-to-use-this-vs-baselines-or-gaps routing and no excluded case. Minimum viable guidance for a tool with several overlapping siblings.

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