mcp_engram_scar

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

With no annotations provided, the description carries full burden. It states the tool creates a 'geometric repeller' and mentions CRS penalty and topological deflection, but does not explicitly disclose whether the operation is destructive, reversible, or requires special permissions. The effect on future inference is described implicitly but lacks concrete safety or side-effect details.

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 front-loaded with 'TRIGGER' and uses three sentences covering trigger, explanation, and alternative usage. While dense with jargon (e.g., 'geometric repeller', 'manifold'), it avoids redundancy and is appropriately sized for the tool's complexity. Could be slightly more terse but 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 5 parameters (including optional ones) and no output schema, the description explains input usage well but does not specify the return value or post-invocation effects beyond the conceptual 'repeller'. Lacks explicit mention of what the tool outputs (e.g., confirmation, error handling) or typical response format. Adequate but with gaps.

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 100%, providing baseline 3. Description adds value beyond schema by explaining concept as 'concept name to scar or uncertainty slug', process_context as emitting 'realized_by edge for process_metrics', and uncertainty_status as scoped to 'recall/memory — not general inference'. This enhances understanding of parameter usage and constraints.

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 trigger condition ('call immediately if code fix fails or user says dead end') and defines tool purpose as creating a geometric repeller to prevent hallucination or reattempting bad solutions. The alternative use for insufficient memory anchors is also explicitly mentioned, distinguishing it from sibling tools like mcp_engram_forget or mcp_engram_remember.

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 when-to-use directive ('Call this immediately') and specifies alternative behavior via uncertainty_status parameter for minting uncertainty receipts instead of guessing. Clearly distinguishes between the two main scenarios, ensuring appropriate tool selection.

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