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

Annotations flag destructiveHint=true and idempotentHint=true, and the description supplies the missing substance behind both: same project is replaced, last 20 entries retained, and a companion CLI command (`ignix-editor direction ... --record`) must be run so the local copy stays in sync. That side-effect disclosure goes well beyond what the annotations say.

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 approval constraint is front-loaded and every clause carries information, including the retention rule and the CLI sync step. It is dense to the point of being a single long run-on block, which slightly hurts scannability but wastes no words.

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 mutation tool with a nested object, no output schema, and partial schema descriptions, the definition covers prerequisites, required fields, overwrite semantics, retention cap, and the required local-sync side effect. There is no 5-with-annotations bar it fails.

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 50% and the nested `direction` object is largely undescribed in the schema, but the description compensates by defining every field's intent: style is the catalog look slug, demo is the feature/screen/result shown, project is the video's folder name, pieces are catalog/block names. Only `workspaceId` is left unexplained, which is a minor residual gap.

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?

Opens with a specific verb+resource ("Save the visual choices of a video") and adds the critical gating condition ("ONLY AFTER the user approved its storyboard"), which cleanly separates it from the read-side sibling get_creative_direction. An agent knows exactly what this creates and under what state.

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?

Gives explicit when-to-use and when-not-to-use rules: only after user storyboard approval, "Never record a rejected proposal or preferences you inferred." It also states the repeat-call behavior (replaces the existing entry), so the agent knows re-invocation is a safe update path rather than a duplicate creation.

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