robot_collapse

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

No annotations are provided, so the description must fully disclose behavior. It mentions removal and promotion but omits important details: whether the operation is destructive or reversible, what happens to class relationships, and the impact on files. Given 14 parameters, the description is insufficiently transparent.

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 extremely concise: two sentences, front-loaded with the main action. Every sentence adds value: the first defines the purpose, the second explains the core logic and key parameters. No filler or redundancy.

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?

Despite having 14 parameters and an output schema (context signal), the description only covers the core algorithm. It does not explain input/output formats, the meaning of common params like verbose or strict, or the structure of the output. This leaves significant gaps for an agent.

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%. The description adds meaning for only 3 of 14 parameters (threshold, precious, precious_terms). The remaining parameters (input, output, working_directory, etc.) are left entirely to the schema, which provides no descriptions. This is barely adequate.

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 ('Collapse class hierarchies') and the resource ('class hierarchies'), with specific behavior regarding intermediate classes and subclasses. However, it does not explicitly distinguish this tool from siblings like robot_reduce or robot_repair, which might also manipulate hierarchies.

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 provides guidance on using parameters like threshold and precious/precious_terms to control behavior. However, it lacks context on when to choose this tool over alternatives (e.g., vs robot_merge) or when not to use it (e.g., if no intermediate classes exist).

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