Supplement Check

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

Annotations only declare the safe-read profile (readOnly, idempotent, non-destructive, open-world), but the description goes far beyond by disclosing the full status vocabulary (above/at/within/no_upper_limit, plus studied-range statuses), the compound-mineral mapping, EPA+DHA estimation for fish/krill oil, UK NHS reference switching, and the adult-only caveat. This is unusually rich behavioral disclosure.

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 core purpose is front-loaded in the first sentence, followed by routing examples and then detailed semantics. It is dense and the later run-on sentences pack many clauses, but nearly every clause (status values, compound field, EPA/DHA, GB handling) carries information an agent needs.

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 no output schema, the description takes on the burden of explaining return values and it does so thoroughly: status enums, compared_with.reference/ depends_on_label, amount.epa_dha_estimate_mg, and the compound field. An agent has everything needed to interpret results and call the tool correctly.

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 the baseline is 3, but the description adds real semantics on top: which units are accepted (IU for A/D/E, DFE for folate), that amounts are per-day, and that country=GB switches the reference to NHS guidance. That meaning extends beyond the schema field descriptions.

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 precise verb+resource+scope: comparing an ingested amount of a vitamin/mineral against adult RDA and upper limits, with concrete example queries like "is 5000 IU of vitamin D too much?". This is clearly distinguishable from the retrieval-oriented siblings get_nutrient and get_supplement without opening any 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?

The four example questions give a strong, unambiguous sense of when to reach for this tool, and the GB country branch and probiotic/compound handling indicate the supported contexts. However, it never names the sibling tools or states when NOT to use this one (e.g., for plain nutrient lookup use get_nutrient).

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds substantial context beyond that: products are counted at the maximum each label suggests, hidden-amount labels are flagged, fish oil is counted as EPA/DHA, and GB switches to NHS guidance. It stops short of stating rate limits or how ambiguous matches are resolved.

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 with purpose, then examples, then input format, then return shape — a sensible order with no filler. It is somewhat dense and the prose runs long, but each sentence carries usable information.

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?

Though there is no output schema, the description enumerates the return fields (totals with contributing items and upper-limit/NHS comparison, other_totals, items, not_found) and covers edge cases like hidden label amounts and fish-oil EPA/DHA. An agent has everything needed to call it and interpret the result.

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% (baseline 3), but the description goes further: it specifies the semicolon separator, the 6-item cap, and that entries may be product names, barcodes, or amounts, plus the country=GB NHS behavior. This meaningfully extends the single schema line for 'items'.

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: it aggregates everything a person takes and checks the daily totals against adult upper limits. The 'up to 6 items' framing and the request examples ('is that too much?') clearly position it as a multi-item stack check, distinguishing it from the single-dose sibling check_dose.

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 two concrete triggering requests ('I take Centrum, vitamin D 5000 IU and zinc 50 mg, is that too much?' and 'is it OK to take OLLY Sleep with extra melatonin?') that make the use context obvious. It does not, however, name an alternative or state when-not to use it (e.g. single-item questions that check_dose handles).

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

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.

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

Annotations already declare read-only/idempotent/open-world, and the description adds substantial non-structured behavior: what each result block contains, that ambiguous generic names read one common label 'and says so', that salt forms are counted as their mineral with estimated: true, and that country=GB switches dose_check to NHS guidance. This is rich disclosure beyond the annotations.

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 with the essence ('A supplement's label: amounts per serving, upper limit check, halal status and a buy link'), then example queries, then the return shape and edge cases. Dense but every sentence adds operational detail; it runs long for a 4-param tool.

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?

No output schema exists, yet the description enumerates the return structure field by field (dose_check, other_checks, halal, alternatives, halal_options) and covers the two major data quirks (salt forms, omega-3 estimation). Nothing an agent needs to call or interpret results is missing.

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; the description goes further by explaining what country=GB actually changes (NHS thresholds and buy-link site) and how q behaves for generic vs brand names, plus routing to id from alternatives.

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 resource (a supplement's label) and enumerates what it returns: per-serving amounts, upper-limit check, halal status, buy link. This is far more than a tautology, though it never explicitly contrasts itself with the sibling tools check_dose, check_stack, or get_nutrient, leaving the boundary to be inferred.

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 concrete trigger phrasings ('what's in Nature Made vitamin D3?', 'is Centrum halal?') and states the two lookup routes, q or barcode. No explicit when-not-to-use guidance versus check_dose or check_stack, which is the only gap.

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