memory_proposal_decide

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

The description adds important behavior beyond the annotations: acceptance runs the original validated tool, artifacts are kept at observed authority, and failed/interrupted applications are not retried because filesystem writes may already have landed. This is consistent with the destructive, non-idempotent, non-read-only annotations and gives a strong operational warning.

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?

The description is short and front-loaded with the core action. Every additional sentence contributes either eligibility or failure behavior, with no redundant restatement of annotations or 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 behavioral warnings are strong and an output schema exists, so return values need not be described. But with 0% parameter coverage, the description leaves the required id and the accept default undocumented, and it does not connect the tool to memory_proposals as the likely source of proposal IDs.

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 0%, so the description must compensate, but it only implies the accept/reject choice and never documents the required id parameter. It also does not explain that accept defaults to false or what the id refers to.

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?

It states a specific verb pair (accept or reject) and a specific resource (one proposal), so the action is immediately clear. It does not explicitly distinguish itself from nearby siblings such as memory_proposals, accept_candidate, or reject_candidate, so differentiation is mostly carried by the name.

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 gives a clear eligibility condition: only a foreground reviewer may decide. It also warns that failed or interrupted applications are not retried automatically. However, it does not explicitly tell the agent to list proposals first or compare this tool with accept_candidate/reject_candidate.

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