memory_propose

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

With no annotations, the description must carry the full burden. It discloses the key behavioral trait that proposals go to a human review queue and are not active memory, but it does not explain the aftermath (e.g., whether confirmation is returned, if duplicates are allowed, or how review proceeds).

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 concise sentences: first defines the purpose, second provides usage guidance and an alternative. No filler words, proper front-loading.

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 9-parameter tool with no output schema and no annotations, the description gives the essential purpose, timing, and relation to alternative. It does not explain the proposal structure or what happens after submission, but the schema covers the parameters, and the operation appears simple enough.

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 56%, so the description could add meaning, but it does not discuss any parameters. The schema itself describes five parameters and enums for kind and guardrail_level, which is adequate, yet the description offers no additional semantic help.

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 'Propose' and resource 'memory for the human review queue', clearly indicating the action and destination. It distinguishes this tool from siblings by mentioning 'review' and 'becoming active memory', which differentiates it from memory_write.

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 gives a usage context ('Use at SESSION END') and names an alternative: 'Prefer this over memory_write for inferred/uncertain knowledge.' This provides clear guidance on when and when not to use the tool.

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