ingest_dialogue

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

The description implies a write operation ('distill', 'persisted') but lacks detail on behavioral traits such as idempotency, destructiveness, required permissions, or error handling. With no annotations provided, the description carries the full burden, and it does not disclose whether existing data is overwritten or if there are limits on accumulation.

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 two sentences with no fluff. The first sentence captures the core action and the second adds important details about persistence and accumulation. Every sentence serves a purpose.

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 tool that ingests into a complex knowledge graph, the description is incomplete. It does not specify the return value (e.g., success confirmation, graph ID) nor any error conditions. Though the input schema is simple, the lack of output schema and missing behavioral context leaves the agent underinformed.

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?

The input schema has 100% coverage for its single parameter 'turns', with a brief description. The tool description adds no extra meaning beyond the schema; it does not explain how the fields (id, text, speaker, timestamp) are used in the distillation process. Baseline is appropriate.

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's action: 'Distill raw dialogue turns into the Cue–Tag–Content associative memory graph' with specific details about multiple layers (episodic/semantic/topic). It distinguishes from sibling tools like generic 'ingest' or 'distill_failure' by focusing on dialogue and the specific graph structure.

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?

No explicit guidance on when to use this tool vs alternatives. While it mentions 'Multiple calls accumulate,' there is no advice on when not to use it or which sibling tools are better suited for different scenarios (e.g., batch ingestion vs. single-turn processing).

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