memory.propose

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does not state whether proposing mutates state, whether the memory is immediately active or pending approval, what side effects occur, or any authorization requirements. Mentioning Markdown and PostgreSQL metadata hints at persistence but does not explain the tool's behavioral contract.

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 a single short sentence with no redundant text, so it is concise in length. However, it is under-specified: terms like 'canonical' and 'PostgreSQL metadata' add jargon without explanation, and no structure organizes the information that would help an agent use the tool. This is under-specification rather than effective conciseness.

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?

Despite the presence of an output schema, the tool has 12 input parameters, 3 required fields, two enums, and several nullable UUID context fields, all of which are left unexplained. The description gives no guidance on how to select memory_type, what sensitivity levels mean, or how the various IDs relate to the memory being proposed. The definition is far from complete for effective agent usage.

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%, and the description adds no meaning to any of the 12 parameters. It does not explain title, content, memory_type, sensitivity, or the optional context IDs. Even though the schema contains enums and titles, the description leaves the agent without any guidance on how to populate these fields correctly.

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 names a specific verb ('Propose') and a resource ('a canonical memory'), so it is more than a tautology. However, 'canonical memory' is undefined, and the phrase 'backed by Markdown and PostgreSQL metadata' clarifies storage but not the actual operation. It does not explicitly contrast with memory.read, memory.search, or memory.archive, so an agent could not confidently distinguish it from siblings.

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 no guidance on when to use this tool versus alternatives. It does not mention that this is for creating/proposing a new memory while memory.read and memory.search are for retrieval, nor does it state any conditions or exclusions. Usage context is only implicit in the tool name and one-line description.

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