Create a Meta product catalog

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

The description goes far beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing numerous behavioral traits: it refuses ambiguous or unknown portfolio names by listing real portfolios, never guesses, will not let vertical or owning portfolio be changed later, and Meta silently allows duplicate names — prompting Hermoso to preemptively refuse duplicates and report the existing id. It also explains that the confirmation is read back from Meta (only an id returned) and that the tool is free. These are critical non-obvious behaviors that an agent must know to use the tool correctly, and the description provides them all.

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 relatively long but every sentence carries essential information—no filler. It is logically structured: starts with the purpose, then covers portfolio identification (with exact matching rules), then the permanence of vertical/portfolio, then the critical duplicate-name nuance, then response confirmation, and finally cost. The use of 'IMPORTANT' highlights the most critical warning. While it could be tightened, the density is justified for the complexity of the tool.

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 tool with 5 parameters, one enum, and nuanced external behavior, the description is remarkably complete. It covers the full workflow, edge cases (ambiguous/unknown names, duplicate names), permanence constraints, the response format (read back from Meta with only an id), and the credit cost. There is no output schema, but the description adequately explains what the confirmation is. Nothing an agent needs to invoke this 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 coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema. It clarifies that businessId and businessName are alternative ways to specify the owning portfolio and explains how names are resolved (exactly as printed by list_meta_catalogs, refused if ambiguous). It emphasizes that vertical defaults to commerce and is permanent, and explains the purpose and default of allowDuplicateName. This goes well beyond the schema descriptions, which are terse; the description effectively teaches the agent how to use each parameter correctly.

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 clearly states it creates a NEW product catalog on a Meta business portfolio, with a specific verb and resource. It explicitly positions it as the first step in Advantage+ catalog ads ('build it first, then fill it... then point a campaign at it'), which distinguishes it from sibling tools like list_meta_catalogs, update_meta_catalog, and delete_meta_catalog. The purpose is unambiguous and includes context on how it fits into a workflow.

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 gives clear context on when to use the tool (create a catalog before filling it with products) and references list_meta_catalogs for obtaining portfolio identifiers, implicitly distinguishing itself from that read-only tool. However, it does not explicitly contrast with update_meta_catalog or delete_meta_catalog, nor does it state 'use this instead of X when...' — though the distinction is obvious given the create/update/delete split. The detailed guidance on naming portfolios and duplicate handling effectively covers the 'when' and 'how' but lacks an explicit 'when not to use' alternative.

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