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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so safety is covered; the description adds substantive behavior beyond that: numbers come from fixed tables with the model never producing a number, and the tool refuses and refers when the child is too young for home medication. It also discloses the return contents (mg range, ml per strength, interval, daily max, warnings), which the agent would otherwise not know cheaply.

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?

Two dense sentences that are front-loaded with the core action and then the routing guidance. The parenthetical brand list and country example are long but each earns its place by preventing wrong invocations; nothing is redundant padding.

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 an output schema present the description need not enumerate return values, yet it still summarizes them usefully; combined with the refusal path, the country/brand coverage, and the explicit sibling routing, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: the breadth of accepted brand names (35 brands / 57 countries) and the reason country matters (it determines which strength is listed, with a concrete Haiti/Dominican Republic example). Weight is tied to the core computation and age is tied to the refusal behavior, linking parameters to outcomes.

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 resource — computes paracetamol/ibuprofen dose for a child by weight from fixed lookup tables — and explicitly distinguishes itself from siblings by naming paediatric_question_with_sources and oral_rehydration_plan. The scope constraint (only two medicines covered) is also stated.

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?

Explicitly states when to use it ('how much paracetamol or ibuprofen to give a child') and routes the agent elsewhere for two distinct cases: fluids in vomiting/diarrhoea to oral_rehydration_plan, any other medicine to paediatric_question_with_sources. Names the required input (weight).

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