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

No annotations are provided, so the description carries the full burden of disclosing side effects and behavior. It only says the tool is a 'recorder tool' and repeats the name; it does not state whether starting a run creates state, requires prior setup, or has side effects. An agent has no information about what invoking this tool will do.

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 short, but this is under-specification rather than effective conciseness. It front-loads the tool name and a generic 'recorder tool' label, yet the single sentence does not earn its place because it conveys almost no operational meaning.

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?

Despite the low parameter complexity, the description is missing the most basic context: what starting a run means, what it records, and how it relates to the sibling tools. With no annotations and no output schema, the description needed to explain the tool's behavior and lifecycle role but fails to do so. It is inadequate for an agent to select and invoke this tool correctly.

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?

The tool has zero parameters, so there are no parameter semantics for the description to clarify. The schema has trivial 100% coverage because it is an empty object, and there is nothing meaningful missing on the parameter side. The baseline of 4 is appropriate for a parameterless tool.

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 is essentially a label: 'Fractal Research MCP recorder tool: fractal_start_run'. It restates the tool name and gives no verb, target, or behavioral content, so an agent cannot determine what starting a run actually does. It is a tautology rather than a meaningful purpose statement.

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 or when to prefer sibling tools such as fractal_finish_run or fractal_record_agent. The name hints at starting a run, but the description provides no context, prerequisites, or exclusions. This is a case of no guidance rather than misleading guidance.

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