n2_kv_save

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

With no annotations, the description carries the full behavioral burden; it does disclose durability and the important non-terminating property, which is real value beyond the schema. It omits whether repeated saves overwrite prior checkpoints, whether an active session is required, and what a successful call returns.

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, zero waste, with the core action front-loaded and the non-termination caveat immediately after. Only nit is the lowercase start of the second sentence.

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 an 8-parameter save tool with a fully documented schema, the essentials are covered, but the relationship to the kv lifecycle siblings (n2_kv_gc, n2_kv_restore, n2_work_log) and to cleanup protection is left for the agent to infer. No output schema exists, so the description should say more about what persistence guarantees to expect.

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% and every parameter, including the importance threshold semantics, is documented in the schema itself. The description adds no meaning about required fields (agent, project, summary) or optional arrays, so the baseline 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?

Names a specific verb and resource ('Save a durable checkpoint'), which clearly separates it from the read-side siblings n2_kv_load and n2_kv_search. It does not explicitly name any sibling, so differentiation is inferred from the kv_ prefix rather than stated.

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 concrete timing ('during work or before replying') and an exclusion ('does not finish active work') that implicitly routes the agent to n2_work_end when the session should close. It stops short of naming that alternative or stating prerequisites such as whether an active work session is required.

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