sw_lock_analysis

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

With no annotations, the description carries full burden and fully discloses behavior: computes SHA-256, immutable old IDs, tracks metric changes, and marks results as exploratory if inconsistent. This is rich and honest about 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 front-loaded and structured, but includes a long philosophical explanation about multiple comparisons. This is informative but could be shortened; still, it remains focused and understandable.

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 9 parameters and an output schema, the description is not operationally complete. It explains the workflow and integration but leaves all parameter semantics unexplained and does not describe the return value structure beyond prereg_id.

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 coverage is 0% with 9 parameters, and the description does not explain any of them. It mentions 'primary metric' and 'baseline' at a high level but fails to clarify parameters like csi_basis, expected_effect, draft_id, etc. The description should compensate for low schema coverage but does not.

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 function: pre-registering the primary metric and baseline before data generation. It distinguishes itself from siblings by explicitly linking its output (prereg_id) to sw_generate and sw_compare_results, and explains the pre-registration concept.

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?

Explicitly states when to use (before generating data) and describes the workflow: call this tool, get prereg_id, pass to sw_generate, then sw_compare_results judges consistency. It also explains what happens if you change your mind, giving clear usage context.

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