cos_dispatch_formula_run

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

With no annotations, the description carries full behavioral burden and does so well. It discloses approximate token cost (~5k), context rebuild penalty, the explicit opt-in nature, and the status='skipped' fallback behavior. This goes far beyond a simple dispatch description.

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 dense but every sentence earns its place: definition, cost, preferred alternative, explicit use conditions, and fallback. It is front-loaded with 'EXPLICIT, OPT-IN' and has clear structured conditions (a)/(b). No filler.

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 the tool's complexity, the description covers cost, context-rebuild behavior, use conditions, and fallback. The presence of an output schema handles return-value details, so the description remains complete for a dispatch tool without repeating schema info.

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 does not explain any of the 8 parameters (e.g., formula_id, session_id, task_marker, persona_id). While names are somewhat self-evident, the description adds no parameter-level semantics and does not compensate for the missing schema descriptions.

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 uses a specific verb-resource pair: 'sub-agent spawn for one role' via 'formula run'. It clearly distinguishes itself from lazy-loading and implicitly from sibling cos_dispatch_parallel_run by noting 'one role' and explicit opt-in semantics.

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?

Explicitly provides when-to-use vs. alternatives: 'PREFER lazy-loading...' and then lists two concrete use cases (a) long-running work, (b) explicit parallelism. It also gives a fallback instruction when no SDK is available, which is excellent guidance.

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