nmem_recap

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

No annotations exist, so the description carries the full behavioral burden. It usefully discloses per-level token costs and that it restores cross-session state, but never states read-only semantics, what happens when no saved context exists, or whether the level/token_budget interplay can drop content.

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?

Three short sentences, imperative verb front-loaded, and the highest-value instruction (session-start trigger) immediately follows the purpose. Every sentence 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?

Covers purpose, timing, and the primary level parameter for a 4-parameter tool with no output schema and no annotations. It is slightly thin on the interaction between level, compact, and token_budget and on the empty-context case, but the essentials for correct invocation are present.

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 each parameter (level, topic, compact, token_budget) is already documented in the schema, including level's token estimates. The description's level restatement adds nothing beyond that, so the baseline of 3 is appropriate.

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+resource ('LOAD project context') and names the upstream writer (nmem_eternal), so an agent can tell it restores rather than saves. However, it does not distinguish itself from close siblings like nmem_recall, nmem_context, or nmem_situation, all of which plausibly read stored state.

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 an explicit trigger: 'Call at SESSION START to restore cross-session state.' That is a clear when-to-use condition. It stops short of naming alternatives or exclusions (e.g., when to prefer nmem_recall or nmem_context instead), so it lacks the full when/when-not guidance a 5 requires.

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