mimic_ai_knowledge_write

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

The description goes beyond annotations (which only indicate non-readonly, non-destructive, non-idempotent) by disclosing automatic CANDIDATE→VERIFIED promotion, effect of corrections, suppression of conflicts, rule update behavior, and gap reset logic. It also mentions response warnings, providing comprehensive behavioral context.

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 detailed and includes all necessary information for agent use. While it is long, every sentence is meaningful. It could be slightly more structured (e.g., bullet points), but the front-loaded purpose and clear grouping of behaviors make it effective.

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 complexity (multiple arrays and flags), the description covers main flows: automatic promotions, corrections, rejections, conflict dismissal, rule updates, and gap resets. It mentions response warnings but lacks explicit output schema details. However, it is still fairly complete for an agent to use correctly.

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 schema already provides 100% coverage of parameter descriptions. The description adds operational semantics (e.g., how increment_use vs increment_correction interact, the automatic promotion tie to use_count, and the effect of reset_gap_seen_counts on all gaps). This adds value beyond the schema without redundancy.

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 writes pattern→component mappings and DS rules to a knowledge file. It specifies when to call it ('at the end of every successful HTML-to-Figma run'), distinguishing it from the sibling `mimic_ai_knowledge_read`.

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 explicit when-to-use guidance and details the use of various flags like increment_correction, state, dismissed_conflicts, rule_updates, and reset_gap_seen_counts. It explains the automatic promotion logic and warnings, giving complete usage instructions.

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