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

The description directly contradicts the readOnlyHint annotation: it states 'Adds one component to an existing project,' implying a mutation, while the annotation declares readOnlyHint=true. This is a serious inconsistency that misleads the agent about side effects. Furthermore, the description does not clarify whether the operation modifies the project file, and the 'PAID.' cost note is not a behavioral disclosure. The contradiction makes this dimension unacceptable.

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 description is front-loaded with the purpose ('PAID. Adds one component...') and then lists the return payload in a compact list-like fashion. It is dense but not overly verbose, and each clause contributes information about behavior or output. The only minor issue is the lack of separation between purpose and caveats, but overall it is structured well.

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?

Given the tool's complexity—returning a closure, files, provider nesting, and rules—the description thoroughly explains what the agent should expect as output. It also covers exceptions like 'Foundation components need no licence key.' However, it does not mention prerequisites such as project existence or payment enforcement beyond 'PAID.', and the contradictory readOnlyHint muddies expectations. Still, the description is largely complete for invoking the tool 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?

The single parameter 'slug' is fully covered by the schema with an informative description ('the component slug, e.g. "button" or "bottom-sheet"'). The tool description adds no additional meaning about the parameter beyond the schema, so it meets the baseline for 100% coverage. No extra semantic value is provided.

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 clearly states the tool's action: 'Adds one component to an existing project.' This is a specific verb and resource, and it differentiates from siblings like get_component or list_components by emphasizing the install action and the transitive closure result. The distinction is explicit enough for an agent to select it correctly.

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 guidance is given on when to use this tool versus alternative sibling tools. The only contextual hint is 'It replaces fetching /r/*.json by hand,' which is not a sibling tool and provides no exclusion criteria. There is no mention of when not to use it or how it relates to add_screen or emit_app. This leaves the agent to infer use cases.

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