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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context on top: the exact return shape differs for nutrients (rda, upper_limit) versus supplements (supplement, what_studies_looked_at, studied_amounts, ceiling, cautions, source), plus the NIH fact sheet link and the country=GB/NHS variant populating a uk field. With no output schema, this disclosure of the data shape is exactly the missing behavior an agent needs.

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?

The purpose and trigger examples are front-loaded effectively in the opening sentences, but the middle devolves into a very long comma-separated inventory of nutrients and supplements that no agent needs to read to invoke the tool correctly. It is informative but not tight; several sentences could be collapsed into the coverage note.

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?

For a read-only lookup with no output schema, the definition supplies scope, trigger examples, the differing return fields, and country-specific behavior, so an agent can call it correctly. The one genuine gap is sibling disambiguation: get_supplement and check_dose are never mentioned, leaving tool selection partly to inference.

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 goes beyond the schema by enumerating the ~30 nutrients and ~15 supplements accepted for `name` and noting that forms such as magnesium glycinate are handled, which helps validate inputs. The country=GB behavior it repeats is already in the schema, so the gain is incremental rather than decisive.

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 first sentence states a specific resource and what is returned: what a vitamin/mineral/supplement does, adult amounts, limits, cautions and food sources. Example queries and the enumerated coverage areas make the scope unmistakable. It loses a point because it never contrasts itself with the sibling get_supplement or check_dose, leaving the agent to infer the boundary.

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?

Five concrete trigger queries ('what does magnesium glycinate do?', 'is ashwagandha safe?', 'how much vitamin D do I need?') give clear context for when this tool is the right call. There is no explicit when-not-to-use guidance or routing to the siblings check_dose/check_stack/get_supplement, so the guidance stops short of full routing.

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