remove_annotations

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. It does not say whether removal is permanent, what happens if an id is not present on the image, whether the whole image annotation set is rewritten, or what permissions are needed — significant gaps for a mutation tool.

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 tight sentence with the action and the scoping identifiers front-loaded; nothing redundant or padded.

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 no explanation, but for a destructive mutation with no annotations and 0% schema coverage, the description omits reversibility, failure behavior for unknown ids, and its relationship to the other annotation-mutating siblings.

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 0%, so the description must compensate. It loosely identifies both parameters — 'from an image' maps to image_id and 'by their ids' maps to annotation_ids — but adds no format, cardinality, or validity constraints beyond the field names.

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?

Specific verb ('Remove') plus resource ('specific annotations from an image') and the identifier mechanism ('by their ids'). It does not differentiate itself from the close siblings add_annotations and replace_annotations, so an agent must still infer which mutator applies.

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?

No when-to-use guidance is given. The description never states how this differs from replace_annotations (which also alters the annotation set) or add_annotations, so the agent gets no explicit routing rule among near-identical siblings.

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