rlm_state_set

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

Without annotations, the description adds value by mentioning mutation ('Write'), optimistic locking, and optional TTL. However, it does not disclose behavior on version mismatch, error responses, permissions, or idempotency, which are critical for a write operation.

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 a single, front-loaded sentence with no wasted words. It efficiently communicates the core purpose and key features.

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?

Given 6 parameters, no output schema, and the complexity of optimistic locking, the description lacks guidance on return values, error handling (e.g., version conflict), prerequisites (e.g., need to get version first), and overall usage flow. Incomplete for a mutation tool of this nature.

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 50% (only 3 of 6 params have descriptions). The description reiterates 'optimistic locking' and 'optional TTL' already in param descriptions but adds no new parameter-specific insights. It fails to compensate for undocumented parameters like swarm_id, agent_id, key.

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 'Write shared swarm state with optimistic locking and optional TTL' clearly states the action (Write), the resource (shared swarm state), and key characteristics (optimistic locking, TTL), distinguishing it from sibling tools like rlm_state_get and rlm_state_poll.

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 implies usage for setting state with versioning and TTL, but does not explicitly specify when to use this tool versus alternatives (e.g., rlm_remember, rlm_context). No exclusion criteria or context guidance is provided.

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