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

Annotations already indicate readOnlyHint=false and destructiveHint=true, so the write nature is acknowledged. The description adds valuable behavioral details: durability across sessions, TTL default/max, value size limit (8192 bytes), and max keys per namespace (1000). These go beyond the structured annotations, enhancing transparency.

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 sentences, front-loaded with the core action, then constraints. Every sentence is information-dense and earns its place; no fluff or redundancy.

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?

The description covers durability, TTL behavior, size limits, and key namespace limits, which is strong for a set tool. It doesn't explicitly mention overwrite behavior or return value, but these are likely inferable given the destructiveHint annotation and absence of an output schema. Overall, well-rounded.

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 already provides 100% coverage for parameter descriptions. The description adds extra constraints not in the schema: value max size (8192 bytes) and max 1000 keys per namespace. It also reinforces the JSON-encoding guidance for the value, adding value beyond the schema's basic description.

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 clearly states the action ('Store a value durably under (namespace, key) with a TTL') and the resource semantics as persistent memory. It distinguishes from sibling kv_* tools by focusing on the write/set operation and the durability across sessions.

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?

It provides a clear when-to-use context: 'use it as memory between stateless runs.' This implies the appropriate alternative usage (e.g., kv_get for retrieval) but does not explicitly exclude other tools or mention when-not to use it.

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