memory_propose

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

With no annotations at all, the description carries the full burden. It does disclose the important side effects: auto mode persists the memory, review mode queues it. However, it omits details such as what validation means, what happens on invalid input, and whether the operation is idempotent or reversible.

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 very short and front-loaded, with both sentences contributing unique information. It is concise, though the extreme brevity comes at the cost of necessary behavioral and parameter context.

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 five parameters, no output schema, and no annotations, this description is not complete enough. It leaves mode selection, parameter meaning, validation behavior, and return values entirely unaddressed, requiring the agent to rely on guesses.

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 itself does not explain any of the five parameters. The agent is left to guess what 'text', 'kind', 'tag', 'subject', and 'target_path' represent, with no schema descriptions to compensate.

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 uses a specific verb ('Validate') with a clear resource ('durable memory candidate') and adds tangible behavior: auto mode stores, review mode queues. This makes the tool's core function clear even though it does not directly contrast with sibling tools like memory_policy or memory_supersede.

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 mentions two modes but does not explain when either mode applies, how mode is chosen, or when an agent should use this tool instead of siblings like memory_read, memory_forget, or memory_supersede. There is no when-to-use guidance or exclusionary context.

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