mcp_engram_quick_trace

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

With no annotations, the description carries full behavioral burden. It discloses that the tool creates a structured trace:* block with a prev_in_trace chain, implying it is a write operation that modifies state. It also suggests follow-up actions. However, it does not explicitly state side effects, permissions, or whether it is destructive, which could be clarified. Still, the core behavior is transparent enough for an agent.

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 front-loaded with the core purpose and usage, followed by few-shot examples. While somewhat lengthy due to examples, every sentence serves a purpose (guidance, illustration). It could be slightly more compact, but the structure effectively communicates when and how to use the tool.

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 (12 parameters, no output schema), the description adequately covers purpose, usage, parameter interaction, and follow-up workflow. It explains the output format (structured trace:* block with prev_in_trace chain) without an explicit output schema. The inclusion of few-shot examples further completes the context for proper invocation.

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?

Input schema covers all 12 parameters with descriptions (100% coverage). The description adds operational context beyond the schema, such as the chaining usage for 'prev' ('chain prev from trace_chain.head') and practical meaning of 'spatial_context' and 'goal_context' via examples. This extra context helps an agent select and fill parameters correctly, justifying a score above baseline 3.

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 explicitly states 'Low-friction trace capture' and specifies usage 'at every fork' with chaining from 'trace_chain.head'. It clearly distinguishes from siblings by focusing on quick capture and chaining, and the verb 'trace' combined with 'structured trace:* block' precisely conveys the action and output.

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 gives explicit when-to-use instructions ('Use at every fork'), how to chain ('chain prev from trace_chain.head'), and post-edit steps ('run reflection loop or mcp_engram_safe_edit_and_verify'). Few-shot examples illustrate concrete scenarios (e.g., edit fork, post-edit delta), providing clear guidance on when and how to use the tool.

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