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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description adds real behavioral context: extraction status values (pending | done | error), the highlights/extractedTextChars fields, and that includeText controls payload size by returning full extracted text. That last point is genuinely useful operational guidance beyond the annotations.

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?

Front-loads the core action and field list, then moves into downstream routing and the includeText behavior. Information-dense but still readable; a slight trim of the chained navigation clauses would tighten it further.

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?

No output schema exists, yet the description documents the return shape (field order, referenceType enum, extraction object, webSearch), explains the one optional flag's effect, and links referenceIds to the correct follow-up tools. An agent has everything needed to call and consume this tool.

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 0%, so the description must compensate and it does: it explains what includeText=true yields (full extracted text) and ties contentId implicitly to the card whose references are listed. brandId semantics are not addressed, hence not a 5.

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 (references attached to a content card) and enumerates the exact returned fields (referenceType, title, referenceUrl, referenceId). The referenceType enum (video | creator | link | document) further disambiguates from siblings like list_saved_references.

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?

Implicitly scopes usage to per-card references and routes the agent onward: referenceId for videos feeds get_catalog_video, for creators feeds get_creator, and includeText=true retrieves full extracted text. It lacks explicit when-not-to-use guidance (e.g., versus list_saved_references), keeping it below a 5.

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