Supplementscanner

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real value by disclosing that subcategories are included and that responses list available_filters with invalid ids rejected, but says nothing about result ordering ties or pagination behavior.

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?

Three tight sentences, front-loaded with the core purpose, then prerequisites and narrowing options. No filler.

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 filtered list tool with full schema coverage and annotations carrying safety, the description covers prerequisite workflow, filtering contract, and response affordance (available_filters) without needing an output schema.

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 all six parameters are already documented in the schema, and much of the description's filter guidance (available_filters, rejected ids) merely restates it. The description adds only modest context, so 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 and resource — finding cheapest supplements ranked by normalized price-per-unit within a category and its subcategories. The 'price-per-unit' normalization detail makes the ranking criterion unambiguous and separates it from get_product/search_products.

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?

Explicitly frames itself as the primary tool for 'what is the cheapest X?' questions and tells the agent to call list_categories first for a valid slug. It also explains how to narrow results with filters and brand, leaving little inference.

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, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the return content (normalized unit price, bulk tiers, buy link, recent price history) — the closest thing to an output schema here. It omits history window length and result limits, keeping it below 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?

Two sentences, zero waste — the returned-field enumeration is front-loaded and the id-provenance note follows. Every clause 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?

For a 2-parameter read tool with full schema coverage, no output schema and clear annotations, nothing an agent needs is missing: the required id, where to get it, what comes back, and the optional market behavior all resolve.

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%: product_id's numeric origin and the market's accepted values, default, and rejection behavior are all documented in the schema. The description only reinforces that the id comes from find_cheapest or search_products and never mentions market, so it sits at the baseline.

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 (get) and resource (full detail for one product by id) and then enumerates exactly what detail is returned: price, normalized unit price, size, bulk/staffel tiers, buy link, and recent price history. An agent can distinguish this single-product lookup from find_cheapest and search_products 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?

"Use the id returned by find_cheapest or search_products" gives a concrete prerequisite and routes the agent through the sibling tools that produce the required id. It does not state any when-not condition or exclusion, so it falls short of a full 5.

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 real behavioral context beyond them: results are filtered to categories with priced products, counts are live, and prices are normalized with an explicit comparison basis. It stops short of covering pagination, result ordering, or auth/rate-limit behavior, which keeps it from 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?

Two sentences, zero filler. The scope constraint and returned fields come first, and the routing instruction to find_cheapest comes second — front-loaded exactly where an agent needs it.

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 return values and does so field by field, plus explains the filtering rule and downstream use. Minor gaps remain around result ordering and whether the list is bounded, but nothing needed to invoke the 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% — the single optional 'market' parameter is fully documented in the schema with its enum values and nl default. The description never mentions market scoping, so it adds no meaning beyond the schema. Baseline 3 is appropriate when the schema does all the parameter work.

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 (List) and resource (supplement categories) plus the exact scope — only categories that currently hold priced products — and enumerates the returned fields (product count, store count, lowest normalized unit price, comparison basis). An agent can distinguish this from find_cheapest, get_product, and search_products 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?

Explicitly routes the agent: "Use this to discover a valid category_slug for find_cheapest." That names the alternative tool and the condition that selects it, which is exactly the decision an agent needs to make between listing categories and searching products.

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, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered. The description adds genuine context beyond that: typo tolerance in name/brand matching, natural-language interpretation in some markets, cheapest-per-unit ordering, and an interpreted_as field explaining how the query was read. It stops short of describing pagination or result volume behavior.

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?

Three dense sentences with the core purpose front-loaded and the sibling routing at the end. Some clauses (the market-reading caveat) are packed tightly, but no sentence is filler.

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 six-parameter, no-output-schema search tool, the description covers the query contract, the interpretation feedback, the ordering guarantee, and the market caveat. The one gap is that return shape beyond interpreted_as (e.g. what fields each product carries) is unstated, despite there being no output schema to lean on.

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 still adds value by explaining the query's own-words semantics with typo-tolerant examples and by noting that stated qualities are turned into category filters, plus the interpreted_as feedback, which is not visible in the schema.

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 (search) and resource (the whole supplement catalog), scopes it as mirroring the website search box, and distinguishes itself from find_cheapest by name. An agent can identify what this does and what it returns 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?

Explicitly says to use find_cheapest when the category is already known, which is a real routing rule. It does not cover get_product for when a specific product identity is known, so alternative guidance is complete for one sibling but not all.

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