Fold Laboratories Art Catalogue

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely useful domain behavior — that inventory is volatile because works are unique or from small editions and can sell between search and checkout. It does not disclose what the call returns (availability flags, partial-batch behavior), which is a meaningful gap for a check tool with no output schema.

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 short sentences, front-loaded with the action and timing, followed by the rationale and the imperative. Every sentence carries a distinct load with 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 check tool with no output schema, the description never says what comes back or how to interpret a partial batch of sold listings, leaving the agent to guess the response contract. The timing guidance is complete, but the return-side completeness is not.

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% and the single parameter is documented there as 'listing_id values from get_artwork.' The description adds no additional semantics about the batch (e.g., mixed available/unavailable results, the 50-item cap), so it neither compensates nor detracts.

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 names a precise verb and resource ('re-check whether specific impressions are still purchasable') and states the scope (specific listing_ids, just before presentation or purchase). An agent can distinguish this freshness check from get_artwork (retrieval) and search_artworks (discovery) 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?

It gives an explicit trigger ('immediately before presenting them to a buyer or attempting a purchase') and a hard directive ('ALWAYS call this before offering a specific impression'), plus the consequence of skipping it. The when-not is stated as an outcome: offering a sold original is worse than offering nothing.

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, non-destructive, closed-world), so the description's job is to add operational context — and it does: only purchasable works are returned, off-sale works never appear, seller-stated attributes may be null, and the 'completeness: partial' flag signals truncated scans. It stops short of describing result ordering or the shape/structure of the verification block, which the response payload carries instead.

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?

Long but front-loaded and dense with actionable constraints; nearly every sentence carries a distinct warning or behavior. The repeated 'IMPORTANT:' markers add some visual noise and the sold/off-sale rules are stated twice (once in prose, once implicit in the schema), which slightly dilutes efficiency.

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 full burden of explaining returns and it does: it points to the `completeness` field, the `_verification` response field, and the per-result verification block, and it warns that null attributes mean unspecified. An agent has enough to call the tool, interpret the response, and avoid reporting incomplete results as exhaustive.

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 contributes real semantics beyond the schema: it explains that a budget embedded in the query string is silently ignored and must be routed to min_price_usd/max_price_usd, and that include_sold controls visibility of sold works. It does not add anything for seller_stated_tags_only or limit beyond what the schema already states.

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 ('Search original artworks') and immediately pins down the matching model as semantic/meaning-based rather than keyword. The scope is further clarified as 'purchasable now' with sold works opt-in, which separates it cleanly from get_artwork (single-item retrieval) and check_availability.

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 context (natural-language subject/mood/palette queries) and multiple when-not rules: price must go through min_price_usd/max_price_usd rather than the query text, authenticity cannot be filtered at all, and include_sold is required to see sold works. Those are exactly the failure modes an agent would otherwise hit.

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