mcp_engram_summarize

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

No annotations provided, so description carries full burden. It discloses return order (pinned first, then top N by CRS), and appends a system_state_vector health line updated every 60s. This is rich behavioral context beyond basic read operation.

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 appropriately sized and front-loaded with the main purpose. Every sentence adds value: usage, ordering, health line details. No redundancy or fluff.

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 complexity of sibling tools, the description is thorough. It explains return format, ordering, and health line frequency. Without an output schema, it still sufficiently describes what the agent will receive.

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 (top_n) with 100% schema coverage. The schema already documents default and description. The description adds meaning by explaining the ordering logic (pinned first, then top N) and the role of top_n in selecting non-pinned memories, which goes beyond the schema.

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 returns a project-state digest with pinned memories first, then top N by CRS score. It uses specific verb+resource and distinguishes from siblings like mcp_engram_recall by saying it's a single call replacing multiple queries.

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?

Explicitly says 'WHEN TO USE: at the start of a new session when you need to rehydrate context fast. Single call replaces multiple recall queries.' Also mentions it's ideal as a /wake_up replacement, providing clear context and alternatives.

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