roasr_vision_analyze

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the video transcript is only returned 'when available' and that the tool does not initiate analysis itself ('if it has not been analysed yet, start the analysis inside the app'), implying a read-only retrieval behavior. It lacks details like error behavior or rate limits, but for an analysis tool the key behavioral traits are conveyed.

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 only two sentences, with each sentence earning its place: the first defines what the tool does, and the second provides the prerequisite workflow. There is no fluff or repetition beyond the source reference, and the phrasing is direct and scannable.

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 a single parameter and no output schema, the description covers the essential contexts: what the tool returns, a conditional output (transcript), and the prerequisite step (spy_search + analyze inside app). It does not detail return formatting or edge cases, but for a tool of this complexity the description is sufficiently complete to set expectations.

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?

The schema already provides the parameter description 'creative ad_archive_id (from roasr_spy_search)', which fully explains the parameter's meaning and source. The description repeats this by telling the user to find the creative with roasr_spy_search first, adding no new semantic detail beyond what the schema already provides. Thus the baseline of 3 is appropriate.

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 performs vision analysis on a competitor creative referenced by ad_archive_id, listing specific output types (hook, angle, format, strengths, risks, transcript). It also distinguishes itself from the sibling metrics tools by stating it provides 'Analysis the plain metrics tools do not have', which helps differentiate from the surrounding tools.

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 offers actionable workflow guidance: first find the creative using roasr_spy_search, then use this tool. It also implies a precondition (the creative must already be analyzed, otherwise start analysis inside the app). While it does not explicitly list when not to use the tool, the contrast with metrics tools and the explicit prerequisite provide clear context for selecting this tool.

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