Fold Laboratories Art Catalogue

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

With no annotations, the description carries the full burden and does well: it discloses that availability is transient, that impressions can sell between search and checkout, and that calling this check prevents offering sold originals. It does not describe the exact return shape or error behavior, but the core read-only re-check behavior is clearly conveyed.

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 sentences with no padding: purpose and timing are front-loaded, the reason is given, and the actionable directive closes the description. Every sentence 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?

The definition fully covers when and why to call the tool, and the single parameter is fully documented in the schema. However, with no output schema, the description could briefly clarify what the response indicates for each listing, e.g., whether it returns per-listing availability or throws on sold impressions.

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%, giving the baseline of 3. The schema already documents listing_ids and even ties it to get_artwork; the description adds no additional parameter-level detail, but none is needed given the clear 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?

The description uses a specific verb and resource: 'Re-check whether specific impressions are still purchasable.' This clearly distinguishes it from the siblings get_artwork and search_artworks, which handle retrieval/discovery rather than post-search availability confirmation.

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?

It gives explicit timing: 'immediately before presenting them to a buyer or attempting a purchase,' plus a strong ALWAYS directive before offering an impression. It explains the market context (unique/small editions can sell between search and checkout), though it does not explicitly state when not to use the tool or name alternatives.

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?

With no annotations, the description carries the full burden of behavioral disclosure and succeeds. It explains that null means 'unspecified rather than estimated,' clarifies that AP/PP/BAT are separate objects from the numbered run with different pricing, and reveals that image URLs are temporary with an `expires_at` that must be honored. These are critical behavioral traits beyond a simple 'get detail' statement.

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 main purpose is front-loaded in the first sentence, with each subsequent sentence adding a distinct and necessary caveat: impression structure, null semantics, temporary URLs, and usage instruction. Despite its length, there is no redundancy and every sentence 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 single-parameter read tool with no output schema, the description provides all necessary contextual information: field enumeration, edition nuances, null handling, temporary URL behavior, and usage timing. Nothing critical is missing for an agent to invoke the tool correctly and interpret its response.

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?

The input schema already provides full coverage for the single `artwork_id` parameter with the description 'artwork_id from search_artworks.' The tool description reinforces that the parameter targets a specific artwork but adds no new format, constraints, or semantics beyond the schema. This aligns with the schema coverage baseline of 3.

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 'Full detail for one artwork' and enumerates the exact fields returned (attribution, medium, dimensions, edition structure, provenance, seller, impressions). This is a specific verb+resource that clearly distinguishes get_artwork from the sibling search_artworks (list/search) and check_availability (availability check). An agent can determine this tool's role 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 description explicitly states 'Use this before presenting a work to a buyer', giving a clear when-to-use context. It does not explicitly name alternatives or state when not to use it, but the sibling distinction is otherwise clear and the context is actionable.

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?

With no annotations, the description carries the full burden, and it delivers: it discloses meaning-only matching, that budget/provenance text is ignored, that sold items are excluded unless include_sold is set, that seller attributes may be null, and that the completeness field may be 'partial'. This is exceptional transparency.

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 description is long but every clause earns its place: core purpose first, then critical behavioral caveats in explicit IMPORTANT blocks. The warnings are necessary because the failure mode is silent and costly, and the structure makes them easy to parse.

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?

Given no output schema and no annotations, the description covers the essential runtime behaviors an agent needs: return scope (purchasable-only default), the meaning-matching caveat, how to encode filters, null attribute semantics, and the completeness field. Nothing critical is missing for correct selection and invocation.

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 baseline is 3. The description adds real semantics by explaining how the query parameter behaves (meaning-only, no numeric or provenance filtering) and how min_price_usd/max_price_usd and trust_tier relate to it. This elevates the value beyond the schema alone.

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'), a specific resource ('original artworks'), and a distinctive mechanism ('natural-language description', 'matches on MEANING rather than keywords'). This separates it from the sibling tools and any plain keyword search without opening schemas.

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 clear context: this tool handles natural-language intended-meaning queries, and explicitly warns that price and provenance constraints belong in the dedicated params, not in the query text. It does not explicitly name alternative tools or state when not to use it, so it falls just short of a 5.

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