memory_capture

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

Annotations indicate non-read-only, non-destructive, non-idempotent, and non-open-world, which align with the description's mention of auto-dedup and reinforcement. The description adds valuable context about the dedup threshold and truncation behavior, exceeding annotation coverage.

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?

Two sentences that front-load the core action and follow with usage guidance. Every sentence adds value; no redundancy or fluff.

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 description covers the tool's purpose, dedup behavior, and recommended use cases. It does not mention the output schema or return value, but the context signal indicates an output schema exists, so explanation is optional. Slight gap on session_id provenance.

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?

All parameters have schema descriptions (100% coverage), so the description adds little new per-parameter detail. The overall behavior of auto-dedup is described but not tied to specific parameters significantly.

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 'Capture a verbatim turn' and specifies the auto-dedup behavior, distinguishing it from siblings like memory_recall and memory_reinforce. The verb 'capture' and resource 'verbatim turn' with the reinforcement mechanism make the purpose unambiguous.

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 recommends using it 'for corrections + load-bearing decisions' and notes that auto-dedup reinforces similar content. However, it does not contrast with sibling tools or state when not to use it, leaving some room for interpretation.

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