deep_reference

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

With no annotations, the description carries the transparency burden. It discloses the reasoning steps (FSRS-6 trust scoring, spreading activation, temporal supersession, dream insights, contradiction analysis) and the result shape, which goes beyond a generic 'reason over memories.' It doesn't address cost/latency or explicitly confirm read-only behavior, but the framing implies analysis rather than mutation.

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?

Three sentences, front-loaded with the core purpose and ending with a usage cue. The list of five internal techniques is dense but informative; no filler or redundant restatement.

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 complex no-output-schema tool, it covers what it does, how it does it, what it returns, and when to invoke it. It lacks details on interpreting trust scores or cost implications, but the basics needed by an agent to select and call it are present.

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%, so the description adds little beyond what the input schema already says: 'query' is described as a question/claim/topic and depth is an integer with higher values meaning more thorough. No extra semantics are introduced.

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 frames deep_reference as a synthesis/analysis tool over memories, naming the techniques involved and the concrete deliverables: trust-scored evidence, fact evolution timeline, and a recommended answer. This distinguishes it from simple retrieval tools like search or cross_reference, though it doesn't explicitly name a sibling.

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?

It gives an explicit trigger condition: 'Use this when accuracy matters.' That's a clear high-level guideline, but it doesn't name alternatives or state when not to use it, leaving the agent to infer the boundary versus sibling tools.

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