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

Annotations are all false, so the description carries the full burden. It discloses that it searches concurrently, adapts depth, returns candidates grouped by purpose, attaches a visual board, and provides an editor comparison that may choose KEEP BASE PICTURE / NO B-ROLL. It also clarifies that nothing enters the project until add_stock_media, which is a key side-effect transparency.

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 long but every sentence adds value. It front-loads the project-scoped note and uses clear, purposeful sentences. While it could be tightened slightly, the density is justified by the complexity of the tool. No fluff or repetition.

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, the description is remarkably complete. It explains the input structure, output behavior (grouped candidates, visual board), the editor comparison mechanism, and the absence of side effects until add_stock_media. There is no output schema, so the description fully covers what an agent needs to know.

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 only 33% (project_id described). The description compensates richly: it explains moments require concrete visual queries, purpose, output time, and duration; query_variants are for distinct truthful visual routes; and kind='photo' is recommended for real people/products/places. It also implies orientation is part of the request but not detailed, which is acceptable.

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 the tool researches B-roll as a coherent story sequence, not isolated keywords, and explicitly scopes it to a project_id. It distinguishes itself from simpler keyword searches and notes that media isn't added until add_stock_media, which differentiates it from sibling tools like search_stock.

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 provides clear context: project-scoped, acts on explicit project_id, and advises using kind='photo' when topical video is unavailable. It doesn't name specific sibling alternatives or when to use them, but the guidance on story sequencing and kind selection gives practical direction. The 'Nothing enters the project until add_stock_media' boundary clarifies when not to expect side effects.

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