mcp_engram_forget

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

With no annotations, the description fully carries the burden. It discloses permanent destruction and details what is lost (CRS, Merkle chain, ADR state). Mentions that pinned blocks are deletable. Lacks description of return value or confirmation, but the warning is strong.

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?

Very concise: 3 sentences. First sentence states purpose, second warns, third provides usage guidelines and exception for pinned blocks. No filler.

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 single-parameter destructive tool with no output schema and no annotations, the description covers purpose, usage boundary, behavioral consequences, and distinguishes from an alternative. The agent can confidently decide when to invoke and what to expect.

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?

Only one parameter 'concept' with full schema coverage (100%). The description does not add additional meaning beyond the schema's 'The concept name to delete'. As per guidelines, baseline 3 is appropriate since schema already documents the param.

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?

Explicitly states 'Permanently delete a memory block from the manifold', clearly identifying the action and resource. Distinguishes from sibling mcp_engram_update by noting that update preserves history, whereas this tool destroys it.

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 guidance: 'Only when a concept is completely obsolete or was stored in error.' Tells when not to use: 'If you need to change what a memory says, use mcp_engram_update instead.' Also clarifies that pinned blocks can still be deleted.

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