Get Interface

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds a very actionable behavioral detail: an unpublished name 'fails loudly'. It also states that the return payload is {handle, name, frame}, a clause beyond the annotations. This provides extra transparency that helps an agent anticipate failure modes and success output.

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 three short sentences with mostly valuable content; the issue number and the awkward phrase 'reference-by-name primitive feature tokens ride on' introduce some noise but the core purpose, failure mode, and return shape are front-loaded. It is compact and the main information appears in the first sentence.

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 that has only two required primitive parameters, no output schema, and no nested objects, the description gives the essential contract: it reads a single published interface, names the failure case, and declares the return object. It leaves some room for interpretation around the 'frame' type, but the tool's core API is sufficiently documented for safe invocation.

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 input schema has no parameter descriptions (0% coverage), and the description adds only the context that the interface is read 'by name from a component'. This clearly implies 'name' is the frame name and 'handle' identifies the component, but the description does not explicitly tie each property to its role, nor does it explain the format or constraints. It is iterated enough for knowledgeable agents but does not fully dart the parameters.

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 specific verb ('Read back'), a precise resource ('single published interface FRAME'), and a lookup key ('by name'), which clearly distinguishes it from writing/baking alternatives like publish_interface. The read intent is unambiguous and the tool's scope is tightly defined.

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?

The description implies this tool is meant for reading by name from a component and that unpublished names fail loudly, but it does not explicitly state when to prefer this tool over sibling read tools or casting operations. There is no 'use this when' or alternative compensation, so the agent must infer the appropriate context. Only also mention of 'reference-by-name primitive feature templates' is a faint clue to one use case.

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