compare.plain (development only)

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

No annotations are provided, so the description bears full responsibility for behavior. It reveals that the tool reads both keys and computes the intersection 'IN THE OPEN', implying a potentially insecure or development-only behavior. It also notes the tool is hidden under VTA_MODE=1. However, it lacks details on side effects, security implications, return values, or error conditions, leaving the agent with limited understanding of consequences.

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 concise, consisting of two sentences that front-load the core operation and then add lifecycle context. It avoids unnecessary verbosity. However, the use of specialized jargon ('walked + lit vertices', 'PSI', 'Rung 3') slightly hampers immediate clarity but does not add bloat. Overall structure is efficient.

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 moderate complexity (two parameters, no output schema, no enums), the description provides sufficient context about its development-only nature and hidden status. It lacks information about the return format, possible outputs, or error scenarios, but these are absent from the schema as well. The cryptic terminology and lack of parameter mapping create gaps, but the basic usage context is present.

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 description adds minimal parameter-specific meaning. It mentions 'two keys' but does not differentiate between parameters 'a' and 'b' or explain their roles. The schema itself provides identical generic descriptions for both parameters (JSON object, string, PNG, or path), so the description contributes nothing beyond the schema. The agent must guess which key is which or infer from the operation.

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 states a specific action: comparing two keys and computing their intersection ('∩ of two keys'), with a parenthetical explaining the inputs ('walked + lit vertices, shared PSI elements'). It clearly identifies the resource (two keys) and the operation (computed by reading both). Some jargon remains cryptic, but the core purpose is recognizable and distinct from sibling tools like key_verify or card_verify.

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 usage constraints: it is 'development only', mentions a future replacement (Rung 3 / DH-PSI), and notes it is hidden when VTA_MODE=1. This gives the agent explicit conditions for when not to use it, but it does not explicitly compare to sibling tools or state when to prefer this over alternatives like key_verify. The guidance is useful but not comprehensive.

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