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

Annotations already declare the write, non-destructive, idempotent profile, so the bar is lower. The description still adds real context by framing the entry as unverified self-report captured verbatim in the person's own words rather than a normalized clinical record. It does not discuss what happens on repeated logging or correction.

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?

One short sentence, front-loaded with the action and resource, with the qualifying detail in parentheses. Nothing is wasted.

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?

Adequate for a two-parameter logging tool where the time parameter is fully documented in the schema and no output schema is needed. The reference to a quantity field that does not exist, and the absence of any duplicate-handling note despite idempotentHint=true, leave gaps.

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?

'Con sus palabras' meaningfully tells the agent to pass the user's raw medication name rather than a normalized drug name, which the schema does not say. However it also promises 'cantidad si los da' while the schema has no quantity field, which could lead an agent to look for or invent one. At 50% schema coverage, the time parameter's rich schema description carries that half.

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?

Names a specific verb plus resource ('Apunta un medicamento') and scopes it to a self-reported intake, which separates it from siblings like log_insulin or log_glucose by resource. It stops short of explicitly contrasting with those siblings.

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 implied by 'la persona dice que ha tomado' (record a reported intake), but there is no explicit when-to-use/when-not guidance or pointer to the nearest alternative such as log_insulin for insulin doses.

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