memory_proposals

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful state context beyond that: results are drafts, are newest-first, and are explicitly excluded from recall/memory_list/find_similar/boot digest. It stops short of return format or pagination details, keeping it at 4.

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 short sentences with zero waste; the core purpose and ordering are front-loaded, followed by scope exclusions and next-step actions. Every sentence carries information.

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 zero-parameter read tool with no output schema, the description covers purpose, ordering, lifecycle state, and routing to memory_ratify/memory_reject. The only gap is the shape/fields of a returned proposal, which the absence of an output schema leaves unspecified.

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?

The tool takes zero parameters, so the baseline is 4 per the rubric. There is nothing for the description to disambiguate and it introduces no misleading parameter assumptions.

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?

States a specific verb (List), resource (pending proposals in the capture-propose queue), and scope (newest first). It also positively distinguishes itself from sibling read tools by declaring these drafts do not appear in recall, memory_list, find_similar, or the boot digest.

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?

Explicitly frames these as DRAFTS awaiting ratification and names the two follow-up alternatives with their conditions ('Ratify one with memory_ratify or discard it with memory_reject'), plus the exclusions from other listing tools. An agent knows exactly when this tool applies and what to do next.

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