Image Edit

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

Annotations already declare the safety profile (readOnly=false, destructive=false, non-idempotent), so the bar is lower. The description still adds real behavioral context: the tool persists a manifest, dependency requirements (images extra, local FFmpeg for frame selection), and that source-derived edits keep explicit provenance. It does not clarify whether the original file is ever overwritten, which is the main remaining ambiguity.

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?

Every sentence carries information and the core purpose plus the manifest persistence is front-loaded. The remaining sentences are tightly packed (grid semantics, dependencies, provenance) with no filler. Slightly dense, but nothing is wasted.

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-value explanation is unnecessary, and the 100% schema coverage documents all nested parameters. Given that support, the description supplies what structured data cannot: dependency requirements, coordinate-grid semantics, and provenance guarantees. An agent has enough 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 description coverage is 100%, so the nested crop/cutout/resize/annotation parameters are already documented, making 3 the baseline. The description adds only one semantic detail beyond the schema: coordinates are resolved on the oriented source grid before crop and resize, which clarifies ordering but not formats. It does not explain output_format/quality tradeoffs or the expected_source_sha256 guard.

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 names a concrete verb and resource ('Edit a source image or decoded video frame') plus the persistence side effect ('persist its exact manifest'). It clearly differs from read-only siblings like image_read or media_info. It never names or contrasts with the closest sibling, image_crop, so sibling differentiation is left to inference.

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 gives prerequisites for use ('Requires the optional images extra; frame selection also requires local FFmpeg'), which is genuinely actionable. However, it offers no when-to-use/when-not guidance and never points to image_crop or media_edit_footage as alternatives for simpler cases. Usage is implied by the capability list rather than explained.

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