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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered; the description reinforces it with "Read-only." It adds genuine context beyond the annotations by explaining the traversal order — it reads the Business Center that owns the advertiser account first, then the others the connection can see — which hints at scope and cost. It stops short of stating pagination, latency, or partial-failure 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?

The core verb and resource are front-loaded, followed by the returned-field list and then the exclusions, which is a sensible order. The long enumeration of returned fields is justified by the absence of an output schema, though it makes the first sentence dense. 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?

With no output schema, the description carries the return-value burden and does so thoroughly by naming every field the agent will receive. Combined with the read-only disclosure, the Business Center traversal note, and the explicit exclusions, an agent has enough to call it correctly and interpret results.

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%, with each of folder, account, catalog and language documented in the schema itself, including the enum values. The description adds no meaning beyond that — it does not clarify what "the connection can reach" means for the account parameter or how catalog filtering interacts with folder scoping. Baseline 3 is appropriate when the schema carries parameter semantics.

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 (product catalogs and their product sets), then enumerates exactly what is returned: catalog name/ID, type, country, currency, owning Business Center, and each product set with ID and product count. It also distinguishes itself from catalog-creation and performance-reporting siblings, so an agent can identify it 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?

Gives an explicit when-to-use ("check whether a client has a catalog ready for catalog ads and to get catalog_id and product_set_id") plus explicit when-not boundaries ("does not create catalogs, catalog campaigns or ads, and does not report performance per product"). This routes the agent away from tiktok_create_campaign and tiktok_performance without needing to guess.

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