swarm_blackboard

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

With no annotations provided, the description alone must carry all behavioral disclosure. It fails to state side effects, mutability, persistence, per-action semantics, or requirements. Terms like 'OCC validation' and 'tree merge' imply operations but do not disclose whether state changes are destructive or reversible, leaving the agent entirely in the dark.

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 only one sentence, but it is not appropriately sized because it is dense with jargon yet empty of actionable meaning. It is under-specification rather than conciseness—every term could be omitted without loss since none are explained.

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 tool has 8 parameters, a complex action enum, nested objects, and no output schema, yet the description provides none of the necessary context for an agent to call it correctly. There is no explanation of expected payloads, return values, or interaction with the blackboard, making the tool effectively unusable without external knowledge.

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 0%, and the description makes no attempt to explain any of the 8 parameters or the action enum. The action values (out, rd, in, eval, etc.) are unexplained, and payload, read_set, write_set, and read_version have no semantic context. The description adds zero value beyond the raw schema.

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 mentions 'Swarm blackboard & OCC concurrency' and lists algorithms (Kung-Robinson OCC, Tree-CRDT merge, Linda tuple space) but never states what the tool actually does for the caller or what resource it operates on. It reads as a feature list rather than a clear verb+resource statement, leaving the agent without a concrete purpose.

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?

There is no guidance on when to use this tool versus alternatives, when not to use it, or any prerequisites. The sibling tools are entirely unrelated (cpg_query, rlm_execute, memory_evolve), and the description provides no comparative context, so an agent cannot determine appropriate invocation.

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