Set the water drunk

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the operative detail behind that: it overwrites the day's total rather than accumulating, which is the behavior an agent most needs. It also notes that data.ok signals server acceptance, though it leaves permission/auth context unstated.

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?

Front-loads the core semantic (set/replace) in the first clause, then handles the two edge cases compactly in the following sentences. Slightly dense with three distinct instructions packed into the second half, but no filler.

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 return-value explanation is unnecessary and the mention of data.ok is mildly redundant. Everything else an agent needs to call this correctly — replace semantics, additive workaround, unit conversion, date resolution via the schema — is covered.

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 both parameters are already documented and the baseline is 3. The description adds one genuine relation beyond the schema, the glass-to-ml conversion via get_water's glass_ml, but otherwise restates that water_ml is the day's total.

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+resource with units: 'Set the total water drunk on a day in ml.' It is immediately distinguishable from the read sibling get_water, which it explicitly references for the additive case.

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?

Gives explicit when/when-not guidance: this replaces the day's total, so to add instead the agent should read get_water and send the sum. It also routes the glass-based case through get_water's glass_ml and tells the agent to ask the user when that value is null.

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