nmem_todo

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

With no annotations present, the description carries the full burden, and it does disclose the key behavioral trait: automatic 30-day expiration. It also names the disposal path (nmem_forget). It omits other relevant behavior such as what the call returns (an ID is presumably needed to later forget the item) and whether the write is idempotent.

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 short sentences with no filler; the defining trait (quick, auto-expiring) is front-loaded before the disposal instruction. Every clause earns its place.

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 single-required-parameter write tool with no output schema and no annotations, the description covers lifetime and teardown adequately. It falls short on the return/identifier behavior needed to actually invoke nmem_forget later, and on how it differs from the other memory-writing siblings.

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 100%, so task, compact, priority, and token_budget are all already documented in the schema, including the 0-10 range and default. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 the resource ('TODO memory') and its transient nature ('auto-expires in 30 days'), which implicitly distinguishes it from the persistent siblings nmem_eternal and nmem_remember. However, it never uses an explicit verb like 'create' or 'store', so the write action must be inferred from the required 'task' parameter. Clear but no direct sibling comparison.

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?

Gives one lifecycle instruction — 'Use nmem_forget to close when done' — which tells the agent how to dispose of the item. It does not say when to prefer nmem_todo over nmem_remember or nmem_eternal (e.g., 'for short-lived tasks only'), so the selection guidance against alternatives is left to inference from the 30-day expiry.

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