Judge and rank covers

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context: the 1-4 scoring scale, dual evaluation contexts (full-screen reels feed vs. small grid tile), that output is ranked with concrete fixes, and that an external vision model is required. It stops short of noting model-dependent cost, latency, or failure behavior when no model is configured.

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?

Two sentences, no filler, with the core action and evaluation criteria front-loaded and the prerequisite model requirement trailing as a constraint. Every clause carries information an agent needs.

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 usefully sketches the return shape (per-item 1-4 scores, a ranking, and a list of fixes). Only the input-mode interaction between image_paths and video_path is left unspecified for a tool whose whole value depends on which candidates get scored.

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 67% and image_paths has no schema description at all; the description compensates partly by explaining the '1-4 images or 4 video frames' candidate concept. It does not clarify the relationship between image_paths and video_path (mutually exclusive alternatives?) or what happens if both are supplied.

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 and resource ('Scores ... cover images', or 4 frames from a video), plus the outcome ('Ranks them and lists fixes'). No sibling tool in the list does cover judging, so it is distinguishable at a glance.

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?

Usage is only implied — an agent can infer this is a pre-publish candidate-selection step, but the description never says when to call it or what to use instead (e.g., analyze_post for post-hoc analysis). The one genuinely useful constraint, 'Needs a vision model (Claude, OpenAI, Gemini, Azure)', is a prerequisite rather than a routing rule.

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