Extract memories from interactions

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

With no annotations at all, the description carries the full burden and does it well: it explicitly discloses deterministic behavior, no LLM involvement, dry-run default, and the mutation path when apply=true. This gives an agent a reliable model of side effects before calling.

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 focused sentences front-load the core purpose and then give the key behavioral switch. Every clause earns its place; no filler or redundant restating of the schema.

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 definition is sufficient for correct invocation: purpose, defaults, mutation flag, and provenance are all covered, and the schema documents parameters. It would be slightly stronger if it described the shape of the returned memory candidates, since there is no output schema, but this is a minor gap for a proposal tool.

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 schema already documents all four parameters. The description mainly restates the apply default and adds source=captured context, which is useful but does not add substantive meaning beyond the schema's own descriptions.

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 names a specific verb and resource: 'Scan recent captured interactions ... propose memory candidates'. It also differentiates from memory-write/recall siblings by emphasizing this is a deterministic scanning/proposal step, not direct storage or retrieval.

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 clearly signals the intended workflow: run in dry-run to propose candidates, pass apply=true to persist with source=captured. It does not name sibling alternatives or exclusion conditions, but the use case is clear from the context.

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