log_water

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

With no annotations at all, the description still carries useful behavior: it discloses a compatibility constraint (requires app 3.8+), the fallback chain when ml is omitted (first quick-cup amount, else 150), and the shape of the response (today_ml, goal_ml). It does not state permissions or whether prior logs can be undone, but for a simple append-style logger this is solid coverage.

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?

Three compact clauses, front-loaded with the action, then the version gate, then the defaulting rule, then the return values. No filler; the only mild weakness is that return-value info is folded into the same run-on block rather than separated.

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?

There is no output schema, so describing today_ml and goal_ml is genuinely necessary and done. However, the unexplained id parameter leaves a real hole in a two-parameter tool, and the absence of any annotation means behavioral disclosure rests entirely on this short text.

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 0%, so the description must compensate. It fully explains ml's defaulting behavior, but the id parameter is never mentioned — an agent cannot tell whether it is a cup id, a user id, or a shortcut reference. Half the parameters are explained, so this is partial rather than complete compensation.

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?

"记一杯水" states a specific verb (log) and resource (a cup of water), which is unambiguous on its own and clearly distinct from the read-only sibling water_today. It stops short of naming that sibling or any explicit boundary, so it is clear but not differentiated by the text itself.

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?

Usage is only implied: an agent infers this is the write counterpart to water_today used when the user drinks water. There is no explicit when-to-use/when-not statement or reference to water_today for read-only queries, though the default-fallback rule for omitted ml does give some practical calling guidance.

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