video_restoration_plan

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

No annotations are provided, so the description carries the full behavioral burden and does not meet it. "Evidence-gated" hints at a gating check and "local" implies on-machine processing, but nothing is said about whether files are written, what a "plan" produces, what evidence is required, or what happens on failure — a serious gap for a tool whose sibling set contains both planners and renderers.

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 single fragment is short but under-specified rather than concise — it front-loads nothing actionable and earns no place beyond echoing the tool name. For a tool with a nested opaque input object and a dual plan/evaluate mode, this length reflects missing content, not efficiency.

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?

An output schema exists, so return values need not be explained, but the description still leaves the opaque `request` payload, the plan-vs-evaluate distinction, and any evidence-gating requirements completely undocumented. For a tool with nested object input and no annotations, this is far short of what an agent needs to invoke it correctly.

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 50%, and the single required parameter is an opaque free-form object (`request`, additionalProperties: true) with no description at all. The description adds zero meaning about what belongs in `request`, so it fails to compensate for the coverage gap; only the `overwrite` flag carries semantics, and that comes from the schema, not the description.

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 sentence essentially restates the name's "plan" verb plus an "evaluate" alternative, wrapped in undefined jargon ("evidence-gated", "local restorative work"). It never says what is actually being restored (video? audio?) or what a "plan" artifact is, and it does not distinguish this tool from plausible siblings such as video_rescue_plan, video_ai_upscale, or video_estimate_operation.

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?

There is no statement of when to use this versus the many adjacent planning/estimation tools (video_estimate_operation, video_rescue_plan, video_preflight), no prerequisites, and no exclusions. The "plan or evaluate" split is left unexplained, so an agent cannot infer which mode applies to a given request.

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