get_trend

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and an output schema covers return values, so the bar is lower. The description does add value by naming the statistical method (Mann-Kendall) and the discrete outcome categories, but says nothing about lookback behavior, data requirements, or how significance is reported.

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?

A single front-loaded clause carrying the method and the output vocabulary, with zero filler. It is efficient, though its brevity shades into under-specification rather than true economy.

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?

Output schema handles return values, but with a required, undocumented type_code, an unexplained days window, and no usage context, the description is not sufficient for an agent to invoke this correctly. More must be said about the required identifier and the time window.

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% with two parameters, one required. The description never explains what type_code identifies (a marker id? a code system?) or that days is a lookback window (default 1825 ≈ five years). It leaves both parameters semantically opaque.

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 computation (marker trend via Mann-Kendall) and names the returned categories (increasing/decreasing/no_trend + significance), which is far more specific than the bare name 'get_trend'. It does not, however, distinguish itself from siblings like query_observations or get_timeline that also surface health data over time.

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?

No when-to-use guidance, no prerequisites, and no alternatives named. The agent cannot tell from the description when a statistical trend call is preferable to the query/timeline siblings, nor what 'marker' covers.

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