get_glucose_history

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the return format ('array of timestamped glucose values') and the default behavior ('Default retrieves 24 hours of data'). This is sufficient for a simple read-only operation, though it does not disclose details like chronological ordering or unit of measure.

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 three succinct sentences, each adding distinct value: purpose, return type, and common use cases with the default behavior. There is no redundancy or fluff, and the most important information is front-loaded.

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?

For a simple tool with one optional parameter and no output schema, the description is complete: it explains what the tool does, what it returns, and the default window. It omits minor details like timezone or units, but these are not critical for a basic history retrieval tool given the clarity of the schema.

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 covers 100% of parameters with detailed information: range (1-720), default (24), and examples (1, 8, 168). The description adds only a reinforcement of the default, providing no additional semantic value beyond the schema. Baseline 3 is appropriate when schema does the heavy lifting.

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 retrieves historical glucose readings, using a specific verb ('retrieve') and resource ('historical glucose readings'). This distinguishes it from sibling tools like get_current_glucose, which focuses on current readings, and get_glucose_stats, which provides statistical summaries rather than raw data.

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 explicit use cases: 'reviewing past glucose levels, identifying patterns, or checking overnight values.' This gives clear context for when to use the tool, but it does not explicitly mention alternatives or exclusion rules, such as 'for current glucose, use get_current_glucose.'

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