cos_classify_prompt

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

With no annotations provided, the description carries the full behavioral burden. It discloses that the tool is heuristic, sub-second, deterministic, makes no LLM call, and optionally writes a gate marker. This gives a clear safety and performance profile, though the effect of the `record` parameter on persistent state is not explicitly described.

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 four sentences, front-loaded with the core purpose and output, followed by the side effect and key performance characteristics. Every sentence adds distinct value with no redundancy or 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?

The presence of an output schema covers return-value details, so the description's focus on behavior, side effects, and workflow replacement is appropriate. The main gap is the missing explanation of `record` and `agent_dir`, which prevents it from being fully self-contained for parameter-level usage.

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 coverage is 0%, so the description must compensate. It explains `prompt` as the user prompt being read, and loosely implies `record` via the optional gate-marker write. However, `agent_dir` is completely unexplained, and the role of `record` remains ambiguous. The description provides partial but not complete parameter semantics.

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 a specific action ('classifies', 'reads', 'returns', 'writes') and identifies the exact resource and output structure ({complexity, dimensions, reasoning, signals}). It also distinguishes itself from sibling tools by defining its unique role as a heuristic classifier with an optional gate-marker side effect.

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 explicitly says it replaces a manual `write-state.sh .thinking_os-gate` step, giving concrete when-to-use context tied to the enforce-task-start.sh workflow. It does not list alternative tools to use instead, but the guidance is strong enough to understand the primary use case.

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