Supplement Check

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

Annotations already declare it safe, idempotent and read-only, yet the description adds substantial behavior: the status enum values for both nutrients and other supplements, compound handling, EPA+DHA estimation for fish oils, and the country=GB switching to NHS guidance. This is well beyond what annotations or schema convey.

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 examples are front-loaded, which is good, but the body is a dense run-on with sentence fragments ('For other supplements the answer compares...') and a truncated final clause ('with a note'). Every sentence is informative, but the structure makes it hard to scan.

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 the description carries the return-value burden and does so: status values, compared_with.reference/depends_on_label, amount.epa_dha_estimate_mg and the compound field are all explained. For a zero-required-parameter tool with optional inputs, nothing essential 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 unit/amount/country/nutrient are already documented. The description restates unit handling (IU, mcg, mg, g, DFE) but adds little syntax or defaulting detail beyond the schema, so the baseline 3 applies.

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: comparing an intake amount against adult RDA and upper limit, with four concrete example questions that make the scope unmistakable. It is clearly distinct from the sibling lookups (get_nutrient, get_supplement) because it returns a safety verdict rather than a nutrient fact.

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 example questions ('is 5000 IU of vitamin D too much?', 'is 300 mg of caffeine too much?') give strong implicit guidance on when to reach for this tool. However, there is no explicit when-not-to-use statement or routing to the sibling tools for plain nutrient lookups.

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 cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive behavior beyond them: a 6-item cap, products counted at the most each label suggests per day, fish-oil amounts counting EPA+DHA, and how hidden amounts are flagged. This is rich context an agent could not infer from structured fields.

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 followed by examples and return shape; every sentence carries information. It runs long, but no sentence is filler given the absence of an output schema.

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 proactively describes the return shape (totals with sources and UL comparison, other_totals, items, not_found), and the input constraints are fully covered. An agent has everything needed to call and interpret it.

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 adds value over the schema: the 'up to 6 items' limit, semicolon separation, and the country=GB NHS-guidance behavior beyond the schema's terse example.

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-and-resource: 'Add up everything someone takes and check the daily totals against adult upper limits.' The multi-item 'stack' scope implicitly separates it from check_dose (single dose) and get_nutrient, though no sibling is named explicitly.

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 explicit when-to-use examples ('I take Centrum, vitamin D 5000 IU and zinc 50 mg, is that too much?'), which anchors the trigger condition well. It does not name an alternative or state when NOT to use it (e.g., for a single item, use check_dose).

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 only declare the safety profile (readOnly, idempotent, closed-world), so the description adds substantial non-redundant context: supplements return different fields (supplement, what_studies_looked_at, studied_amounts, ceiling, cautions, source) instead of rda/upper_limit, the NIH fact sheet is linked, and country=GB changes both the amounts shown and the shop link site. That is exactly the behavioral detail the annotations cannot convey.

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 core purpose and example queries before the long enumerations, so the key information is reachable immediately. The extensive nutrient and supplement lists are somewhat repetitive — "vitamin, mineral" already implies the enumerated vitamins — but they plausibly earn their place for matching free-text name inputs.

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 correctly compensates by describing the returned fields, the conditional nutrient-vs-supplement shape, and country-specific behavior; annotations cover safety. The only notable omission is any statement of how this differs from the sibling get_supplement.

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 it by explaining that country=GB yields UK/NHS amounts surfaced in a uk field and also selects the shop link site. It also confirms name accepts both straight nutrients and common forms (e.g., magnesium glycinate).

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 and resource precisely: it returns what a vitamin, mineral or supplement does, adult requirements, limits, cautions and food sources. An agent can tell what it retrieves without opening the schema. It does not, however, differentiate itself from the sibling get_supplement, which looks like it overlaps heavily with the supplement half of this tool.

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 anchored by concrete trigger phrasings ("what does magnesium glycinate do?", "how much vitamin D do I need?", "is ashwagandha safe?") that make the intended question type obvious. It also clarifies the nutrient-vs-supplement split in outputs. It stops short of naming when to choose check_dose or get_supplement instead.

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 establish read-only, idempotent, non-destructive, closed-world behavior, yet the description adds substantial undisclosed-by-schema traits: fallback behavior for generic names ('reads one common label and says so'), country-dependent NHS guidance, and estimation flags (estimated: true for salt forms, omega-3 derived from EPA/DHA). These caveats materially affect how an agent should interpret results.

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 lead sentence front-loads the resource and its outputs, and the use-case examples follow logically. It is dense and packs return fields into two very long sentences, but with no output schema most of that detail earns its place.

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 carries the burden of describing returns, and it does so thoroughly (dose_check, other_checks, halal, alternatives, halal_options, Amazon link) while covering edge cases like blends and generic names. Nothing an agent needs to call and interpret this tool correctly 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 description coverage is 100%, so all four parameters are already documented (q, id, barcode, country including GB/NHS behavior). The description largely restates these ('Give q (brand and product name) or barcode') and adds only marginal context, so the baseline 3 applies.

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 states a specific resource and scope: a supplement's label with per-serving amounts, dose check, halal status and buy link. An agent can tell what it returns without opening the schema. However, it never names or contrasts with the overlapping siblings (check_dose, get_nutrient, check_stack), so it misses the sibling-differentiation bar for a 5.

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?

Concrete example questions ('is Centrum halal?', 'how much melatonin is in OLLY Sleep?') give clear context for when to reach for this tool, and it states the input forms (q or barcode). It lacks any when-not guidance or routing to the sibling dose/nutrient tools, which matters given the overlap with check_dose.

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