sweep_noise

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

With no annotations, the description must disclose side effects and safety. It states it updates signal_score, but doesn't clarify whether moments are deleted, marked, or otherwise changed, nor the reversibility or impact on linked data. This is a significant gap for a mutation tool.

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 sentence that front-loads the action and efficiently lists the noise types with a semicolon-separated list. No wasted words.

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?

For a mutation tool with no output schema and no annotations, the description lacks critical contextual information: what happens to the moments (delete vs mark), what the return value is, and the exact effect on signal_score. This prevents an agent from fully anticipating the tool's behavior.

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 descriptions cover 100% of parameters with type and default information. The tool description adds no parameter-specific semantics, but the schema is self-sufficient, so baseline 3 applies.

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 identifies the operation (denoise) on a specific resource (auto-marked moments) and enumerates noise types (trivial, duplicates, cooldown) and the side effect (updates signal_score). This distinguishes it from sibling tools like list_moments or mark_moment.

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 the tool is for cleaning up auto-marked moments when there is trivial/duplicate/cooldown noise, but it doesn't explicitly state when to prefer this over alternatives or mention any exclusions. No alternatives are named.

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