mcp_engram_recall

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

With no annotations, the description fully discloses behavior: explains output (concept name, score, CRS, text snippet), score thresholds (>0.80 strong, 0.65-0.80 relevant, <0.65 weak), CRS meaning (>=0.74 grounded fact), scope defaults to ENGRAM_MEMORY_MODE, time_decay applies backward unitary operator, and zedos_filter values with detailed explanations. No contradictions.

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 long but well-structured with sections (WHEN TO CALL, OUTPUT, ZEDOS FILTER GUIDE, TIME DECAY). Every sentence adds necessary context given the tool's complexity. Could be slightly more concise, but the structure aids readability.

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 search/recall tool with no output schema, the description covers output format, score interpretation, CRS meaning, parameter usage, follow-up tool recommendation (mcp_engram_read_concept), and ties into broader system concepts (ENGRAM_MEMORY_MODE, ZEDOS_TRAINING, Phase 2 WS2-B). All essential aspects are addressed.

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%, but description adds substantial value: explains scope default behavior (follows ENGRAM_MEMORY_MODE), time_decay trigger condition and semantics, zedos_filter options with deep explanations (e.g., 'training selects ZEDOS_TRAINING blocks with richer 8-property CLS tuples and NREM bias'). This goes well beyond the schema descriptions.

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?

Clearly states 'Search persistent memory by semantic similarity. Returns ranked HolographicBlock memories.' The verb 'search' and resource 'persistent memory' are specific. The output description further clarifies the tool's function, distinguishing it as the primary recall tool among many siblings.

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?

Explicit 'WHEN TO CALL' section advises using before answering technical questions, editing files, or making architectural decisions. Also specifies that time_decay is only for past-work queries. Lacks explicit when-not-to-use or alternatives, but the positive guidance is strong and actionable.

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