cos_promote

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

The description states 'Creates file content but does NOT write to disk', which directly contradicts the annotation readOnlyHint=false that implies the tool may have side effects. This is a serious inconsistency. While the description does add useful behavioral context (e.g., return format, confidence threshold), the contradiction warrants a score of 1.

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 compact and well-structured: a one-sentence purpose, a prerequisite line, a behavioral line, and clean Args/Returns sections. Every sentence adds value, and the most important information (purpose, side-effect-free generation) is front-loaded.

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 only two parameters, the description is complete: it specifies the prerequisite, the non-writing behavior, the caller's responsibility, and the return format. It provides enough context for an agent to invoke it correctly and handle the output, even without an explicit output schema.

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 input schema has zero descriptions (0% coverage), so the description shoulders the full burden. It explicitly documents pattern_id as 'ID in learned_patterns table' and target as an output type with allowed values 'feedback' or 'rule', fully compensating for the schema's lack of explanation.

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 'Promote a validated pattern to a rule or feedback memory file', giving a specific verb and target resources. It distinguishes from sibling tools by focusing on promotion of already validated patterns, not validation or suggestion.

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 a key precondition (confidence >= 0.3) and explains that the tool does not write to disk, implying it should be used as a content generator with caller-driven persistence. However, it does not explicitly mention when to use this tool over alternatives or provide exclusions relative to sibling tools.

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