Log a dose

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

Annotations are minimal (no read-only, no idempotency, no destruction hints), so the description carries the full burden of disclosing behavior. It transparently warns that a safety guard may refuse duplicate or too-soon doses, prohibits silent retries, requires explicit confirmation before using override flags, and describes ambiguity resolution via candidates. This is strong behavioral context beyond what any annotation or schema field provides.

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 compact, front-loaded with the core action, and uses a clear, readable structure for the refusal and ambiguity scenarios. Every sentence earns its place: no filler, no restating of obvious schema fields, and no ambiguous pronouns. The contrast between 'do NOT retry silently' and 'then call again' makes the workflow easy to follow.

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?

Given the complexity of the tool (5 parameters, mutable state, safety guard, output schema), the description covers all the non-obvious context an agent needs: how to phrase medication input, how to handle guard refusals, when to use override fields, and what to do with ambiguous candidates. Return-value details for normal success are reasonably delegated to the output schema, and the safety-critical behaviors are fully disclosed.

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 coverage is 100%, so the baseline is 3. The description adds practical meaning beyond the schema: medication should be recorded exactly as the elder spoke it ('my blood pressure pill' works), and the overrideReason should contain the elder's own words for why the extra dose is needed. It also ties confirmOverride/overrideReason to the refusal flow, which enriches the parameter semantics.

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 opens with a specific verb and resource: 'Record that the elder took a medication' and immediately clarifies the input style as 'name as spoken', including brands and colloquial phrases. This clearly distinguishes it from siblings like skip_dose (which records omission) and add_medication (which adds a medication definition).

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 gives explicit procedural guidance for the two main edge cases: safety-guard refusal and ambiguous medication names. It states when to retry (only after elder confirmation with overrideReason), when to ask the elder, and how to handle candidates. It does not explicitly contrast with alternatives such as skip_dose, but the 'took a medication' framing makes the primary use case unmistakable.

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