find_outdated_products

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

With no annotations provided, the description carries the full burden — and it delivers. It discloses that the call is non-mutating ('Nothing is changed'), explains the heuristic nature and lack of a native 'outdated' concept in the Vendor Center API, and describes the return structure including the flattened listing rows with variation_id, seller_sku, and business_client_code. This is exemplary 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 description is a single focused paragraph with three distinct sections: what the scan finds, the heuristic caveat and non-mutating guarantee, and the exact return format including how rows map to deactivate_products inputs. Every sentence adds essential guidance; there is no filler. The most important information is front-loaded.

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 the tool's complexity (8 unannotated parameters, no output schema), the description covers the operation-level behavior and return shape thoroughly, but it leaves parameter semantics completely undocumented. It explains what the tool does and what the output looks like, but not how to tune the scan thresholds or scope it to a shop/category. The core value is strong; the missing parameter context is a notable gap.

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 0% and the description does not explain any of the eight parameters by name. While the prose mentions the broad heuristic criteria (QC-rejected, zero stock, stale ACTIVE), it never ties these to parameters like zero_stock_grace_days, qc_rejected_grace_days, stale_active_grace_days, max_products_scanned, shop_id, or category_code. The schema provides no descriptions, so the agent is left to infer parameter meaning from names alone, which is insufficient.

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 ('Scan the catalog') and clearly defines the resource and criteria: QC-rejected and never fixed, ACTIVE with zero stock for a long time, or ACTIVE and untouched for a very long time. It also clarifies that the tool is a heuristic scan, not a deletion queue, which distinguishes it from deactivate_products and other sibling tools. The purpose is unmistakable.

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 explicitly states that calling this tool changes nothing, and instructs the agent to pair it with deactivate_products() after human (or deliberate AI) review. It also warns against treating the output as an automatic deletion queue, which is a clear guideline for when and how to use the tool. No alternatives are named, but the pairing and cautionary note provide strong usage direction.

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