record_medication

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

Annotations already declare write/non-idempotent/non-destructive, so the bar is lower. The description still adds meaningful behavior beyond them: entries are 'stored immediately as approved', i.e. no staging or review step, and defaults are stated (product_type prescription). It does not describe duplicate handling or error behavior, keeping it short of a 5.

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-loaded purpose followed by parameter guidance and a boundary statement; every clause earns its place. The semicolon-chained delivery is dense and slightly run-on, which costs a point against a cleanly separated layout, but nothing is redundant.

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?

An output schema exists so return values need not be explained, and the description covers all parameters plus the key behavioral fact (immediate storage) and a hard usage boundary. Only minor gaps remain — behavior on re-recording an existing medication or how this interacts with pending-review tools.

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 carries the full burden — and it does so for all 8 params: medication_name (brand or generic), start_date format (YYYY-MM-DD), dose_amount+dose_unit pairing with an example, times_per_day, product_type enum values with the default, prescribed_for, and atc_code optionality. This is exactly the compensation the schema lacks.

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+resource ('Add a medication or supplement') and immediately narrows scope with 'the user currently takes', which cleanly separates it from read tools like get_medications and from the other record_* siblings. An agent can identify the operation without opening the schema.

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?

Provides real usage conditions: 'record these whenever known' for dose fields, points to check_medication_safety as the consumer of dose data, and gives an explicit exclusion ('Never use this to change a prescribed dose — that is for the doctor'). It does not contrast with siblings like record_allergy/record_diagnosis, but the context is otherwise clear.

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