omega_cortex_steer

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

No annotations provided, but description carries burden well. It discloses the core behavior (block, steer, pass) based on similarity, and specifies the JSON return structure with fields. However, it does not explicitly mention side effects (e.g., logging, persistence) or whether the tool modifies state beyond returning a result.

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?

Description is single paragraph, front-loading purpose and sibling distinction, then thresholds, then return format. Every sentence adds value; no wasted words.

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 no output schema, description fully specifies the return format (JSON with similarity, steered_args, corrections, verdict). It covers inputs, behavior thresholds, and differentiates from sibling. All necessary context for an AI agent to use this gate tool correctly 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?

Input schema has 100% description coverage – each parameter is already clearly explained. The description adds no further detail about individual parameters beyond what schema provides, but it contextualizes them within the tool's behavior. Baseline score of 3 is appropriate.

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?

Description clearly states it's an alignment gate with automatic argument correction, and explicitly distinguishes from sibling omega_cortex_check by specifying when to use this tool ('Use this instead of omega_cortex_check when you want arguments auto-corrected'). The verb 'steer' and resource 'tool arguments' are specific.

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?

Provides explicit thresholds for when to use: similarity < 0.45 blocks, 0.45-0.65 steers, > 0.65 passes unchanged. Also names the alternative (omega_cortex_check) and the preferred use case (when auto-correction desired).

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