sw_compare_results

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

No annotations are provided, so the description carries the full burden. It discloses that the tool uses the same paired-test/gating implementation as sw_compare_arms, warns that mismatched data can still produce a seemingly significant p-value, and details the blocking conditions. It also describes what the returned statement contains. This is thorough and goes beyond a simple read-only or mutation hint.

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 organized into three short paragraphs, front-loading the core purpose. Every sentence adds value: differentiation, validation, warning, and output. It is somewhat verbose but still efficient, and the bolded warnings improve scannability. It earns a 4 rather than 5 because it could be slightly tightened without losing information.

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 moderate complexity, the description covers the main aspects: purpose, usage differentiation, validation conditions, behavioral edge-case, and output statement. However, it leaves claimed_gain completely unexplained and assumes domain knowledge about gates 2 and 3. The existence of an output schema reduces the need for return-value detail, but the param gap keeps this from a 5.

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%, so the description must compensate. It clarifies that result_id_a and result_id_b are two external algorithm results, which adds meaning beyond the raw parameter names. However, the third parameter claimed_gain is never mentioned, leaving its purpose ambiguous. Thus the description only partially explains 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 opens by stating the tool's function: '判决两个外部算法结果' (judge two external algorithm results) and explicitly mentions passing gates 2 and 3. It clearly differentiates itself from the sibling tool sw_compare_arms by noting that while it uses the same statistical implementation, it reads registered results rather than running built-in precoding.

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 explicitly contrasts this tool with sw_compare_arms: '那个现场跑内置预编码，这个读已注册的结果' (that one runs built-in precoding on the spot, this one reads registered results). This tells the agent when to choose this tool over the alternative. It also lists three registration consistency checks that will block execution if not satisfied, providing clear prerequisites.

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