CGM daily summary

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds significant behavioral context: it explains that the actual computed window (hours_covered) can be shorter than the requested window due to FreeStyle Libre's ~12h cap, and that notes flags this. It also warns against overstating coverage. This goes beyond the annotations and is crucial for correct interpretation of results. No contradiction with 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 two sentences, with the first sentence enumerating the stats and the second explaining the coverage limitation. It is dense with important information and avoids fluff. The critical caveat is front-loaded after the metric list. While slightly technical, it is appropriately sized for the tool's complexity.

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 no output schema, the description explains the key output stats and the crucial caveat about hours_covered. It also specifies time-in-range thresholds. However, it does not describe the exact structure of the returned object (e.g., how 'notes' is presented) or handle edge cases like no data. For a summary tool with this complexity, it covers the essential behavioral and output aspects sufficiently, but a bit more detail on the output format would make it fully complete.

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 100%, so the schema already documents both parameters. However, the description introduces a mismatch: it refers to 'window_hours' while the actual parameter is 'hours'. This creates confusion rather than adding clarity. It also mentions 'hours_covered' and 'observed_window' which are output fields, not parameters. The description fails to reinforce the parameter name and adds potential misdirection, lowering its contribution to parameter understanding.

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 explicitly states the verb 'Returns' and the resource 'daily glucose stats', listing specific metrics (mean, median, stdev, GMI, CV, time-in-range). This clearly differentiates it from siblings like cgm_glucose_now or cgm_time_in_range by specifying the comprehensive summary nature. No ambiguity about what the tool does.

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 provides behavioral context about the hours_covered caveat but does not explicitly state when to choose this tool over alternatives like cgm_glucose_window or cgm_time_in_range. It implies it is for a daily summary but lacks explicit 'use when' or 'use instead' guidance. The note about not reporting beyond hours_covered is a usage rule but not tool selection guidance.

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