Icon Composer MCP

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

No annotations are provided, so the description carries the full burden of disclosure. While it mentions mutation ('Add'), it lacks critical behavioral details: it does not state whether this is idempotent, what happens if the bundle_path doesn't exist, whether existing layers are overwritten, or what the return value indicates. For an 11-parameter file modification tool, this is insufficient safety and behavioral context.

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?

Two short sentences with no wasted words. The primary action is front-loaded in the first sentence, while the second clarifies group behavior. However, given the tool's complexity (11 parameters, mutation semantics), the extreme brevity arguably shifts from conciseness to under-specification in the completeness dimension.

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 tool with 11 parameters that mutates file bundles and lacks annotations/output schema, the description is too minimal. It omits prerequisites (bundle must exist), error handling, idempotency guarantees, and any indication of return value structure. The richness of the input schema highlights the poverty of the descriptive context.

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 parameters are fully documented in the schema itself. The description adds minimal semantic context beyond the schema, though the second sentence ('Creates a new group or adds to existing one') provides some high-level context for the create_group and group_index parameters. With high schema coverage, baseline 3 is appropriate.

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?

States specific verb (Add) and resource (layer to .icon bundle) clearly. The second sentence clarifies group handling behavior, which hints at the create_group/group_index relationship. However, it does not explicitly differentiate from siblings like create_icon (which creates the bundle) or remove_layer, though the distinction is somewhat inferable from the text.

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?

Provides no guidance on when to use this tool versus alternatives (e.g., create_icon for new bundles), nor does it state prerequisites such as the bundle needing to exist beforehand. No error conditions or failure modes are described.

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