images_manage

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

Annotations supply only destructiveHint=true, so the description does add value by stating the workspace confinement and bounded MIME-type constraint. It does not, however, say what is destroyed or overwritten (the embedded image? the target file at outputPath?), nor that expectedRevision/expectedOutputRevision act as optimistic-concurrency preconditions that will fail the call. With annotations covering only the safety flag, some real behavioral burden remains unaddressed.

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?

A single front-loaded sentence with no filler or redundancy. It is dense to the point of being slightly jargon-heavy ('explicit SVG raster images'), but every clause carries information.

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 destructive, union-schema tool with two distinct action branches, optimistic-concurrency tokens, and file output, one sentence is not sufficient. An agent gets no branch-level explanation of what relink versus extract actually do to the workspace or the asset path; the existing output schema covers return values but not intent.

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 oneOf schema is richly self-documenting via const discriminators, enum values, patterns, and additionalProperties:false, so the schema carries most parameter meaning. The description gestures at 'embedding' and MIME types but explains nothing about the two revision parameters, which are the least self-evident fields. Baseline 3 is appropriate when the schema does the heavy lifting.

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 concrete verbs (relinks, embeds, extracts) and a concrete resource (SVG raster images), which is enough to place it against siblings like images_crop, images_trace, or document_import_raster. However, 'embeds' is not actually an action in the schema — it is an 'embedding' parameter value inside the relink variant — so the verb list slightly misrepresents the tool's operation set.

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 when-to-use guidance, no statement of when to pick this over images_crop/images_trace/document_import_raster, and no explanation of when relink is preferable to extract. The description only enumerates capabilities, leaving selection entirely to inference.

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