memory_propose

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

With no annotations, the description carries the burden. It discloses that the memory is proposed for review rather than directly written, and that it's for uncertain knowledge. However, it doesn't detail side effects (e.g., whether it persists immediately, returns a proposal ID, or blocks). This is a gap but the core behavior is clear.

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?

Three sentences with zero fluff. Purpose is front-loaded, usage guidance follows, and the tool is distinguished from memory_write efficiently. Every sentence earns its place.

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 10-parameter tool with full schema descriptions, the description provides sufficient usage context and differentiates from siblings. It doesn't cover return values, but no output schema exists and the core action (proposing to review queue) is clear. Complete enough for an agent to decide when to call.

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 description coverage is 100%, so the baseline is 3. The description adds no parameter-specific details; the schema already documents each parameter, including conditional ones like 'applies_when' and 'guardrail_level'. The description does not need to repeat this.

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 action ('Propose a memory for the human review queue') and explicitly contrasts it with memory_write for inferred/uncertain knowledge. This distinguishes it from sibling tools without requiring schema inspection.

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 gives explicit guidance: 'Use at SESSION END for learnings that should persist but warrant review' and 'Prefer this over memory_write for inferred/uncertain knowledge.' This provides both when-to-use and when-not-to-use conditions, routing the agent to the correct tool.

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