CPersona

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

The description adds valuable behavioral context beyond annotations by clarifying that LLM processing happens externally ('performed by the caller'), establishing this as a pure persistence operation. Combined with annotations indicating idempotency and non-destructive behavior, this creates a clear behavioral profile, though it could mention atomicity or validation behaviors.

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 two-sentence structure is optimally efficient. The first sentence establishes the core operation and required inputs, while the second sentence delivers essential behavioral constraints. No words are wasted, and the critical constraint (LLM processing location) is front-loaded in the second sentence.

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 complete schema coverage and presence of annotations, the description provides adequate context for an archival operation. The sibling tool names (list_episodes, recall) imply retrieval pathways. However, without an output schema, the description could briefly mention success indicators or failure modes.

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?

With 100% schema description coverage, the schema already documents all parameters sufficiently (e.g., 'Space-separated keywords'). The description reinforces that summary and keywords should be 'pre-computed,' confirming the parameter semantics but not adding substantial new information beyond what the schema provides.

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 specific action ('Archive') and resource ('conversation episode'), and mentions the key fields involved (summary, keywords, resolved). It implicitly distinguishes from sibling tools like 'delete_episode' (removing vs. preserving) and 'store' (generic storage vs. episodic archival), though it could explicitly clarify the archival scope.

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 provides critical usage constraints by stating 'All LLM processing is performed by the caller,' indicating when to use this tool (when processing is already complete). However, it lacks explicit guidance on when to choose this over alternatives like 'store' or 'list_episodes', or prerequisites like conversation completion requirements.

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