remember

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

With no annotations, the description alone communicates the critical behavioral trait: the memory is PENDING and does not take effect until human approval. This is a key side effect that agents must know. The CONXT_AUTO_APPROVE hint adds practical detail. No contradiction with annotations (there are none).

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, front-loaded with the core action and approval flow, then a configuration tip. Every sentence earns its place with no fluff or redundancy.

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 tool with 4 parameters, no output schema, and no annotations, the description covers the essential behavioral context (PENDING) and usage context (approval flow). It lacks 'when to use vs. alternatives' and potential error cases, but these are minor for a simple 'propose' tool with well-named siblings.

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 each parameter has a description. The tool description adds no extra parameter-level meaning beyond the schema, such as formatting constraints, examples, or required-value rationale. Baseline 3 is appropriate since the schema fully documents parameters.

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 verb 'propose' with the resource 'a new memory', and explicitly mentions the PENDING state, which distinguishes it from siblings like approve and reject. An agent can immediately grasp the tool's function without ambiguity.

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 clear context by explaining the PENDING/approval workflow and suggests a configuration for solo use. However, it does not explicitly contrast with siblings (e.g., 'use approve to confirm pending memories') or state when not to use it, though the purpose and sibling names make it inferable.

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