auto_capture

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

Without annotations, the description discloses key behavioral aspects: 'Items that pass salience filtering are stored as durable memories' indicates a write side effect, and 'zero LLM calls' offers performance transparency. However, it does not elaborate on deduplication, error handling, or the impact on existing memories, which keeps it short of a 5.

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 three sentences, starting with the core action and resource, then listing detected signal types, then stating the storage outcome and usage trigger. Every sentence adds value, and the key information is front-loaded.

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?

The tool has no output schema and no annotations, so the description should cover return values and edge cases. It explains the storage side effect and usage, but does not mention what the tool returns (e.g., captured items or confirmation) nor behavior when no memory-worthy items are found.

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 baseline is 3. The description's phrase 'analyze a block of conversation text' aligns with the 'text' parameter but adds no extra nuance for 'scope' or 'source' beyond what the schema already 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 uses a specific verb 'Extract' and resource 'memory-worthy items from a conversation turn', clearly stating the tool's function. It lists concrete signal types (preferences, identity facts, decisions, etc.) and highlights the zero-LLM heuristic approach, which distinguishes it from sibling tools like store_memory or distill_memory.

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 explicitly states 'Use this when you want to analyze a block of conversation text and automatically capture any signals worth remembering,' providing clear usage context. However, it does not mention when not to use it, nor does it point to any alternative tools, so it lacks exclusionary guidance.

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