clarik_assumption_checker

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

Without annotations, the description bears full responsibility. It only says 'Flag' but does not clarify output format, side effects, or whether it modifies the response. The read-only nature is inferred but not stated, leaving the agent uninformed about invocation consequences.

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?

Two concise sentences with no redundancy or extraneous information. Every sentence serves a clear purpose.

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 description adequately conveys purpose for a simple checker with two parameters (one optional). However, without an output schema, the agent lacks information on how flags are returned (e.g., as a list, modified response). This is adequate but not fully complete for informed invocation.

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 100% with descriptive parameter names and schema descriptions. The tool description adds minimal extra meaning ('Reviews a response for unverified claims') beyond the schema, which already explains the purpose. At baseline 3, no significant added value.

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?

Description clearly states 'Flag when Claude is making assumptions instead of asking. Reviews a response for unverified claims.' It specifies the verb (flag/review) and resource (assumptions in a response), distinguishing it from siblings like clarik_hallucination_detector or clarik_diff_reviewer.

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?

No guidance is provided on when to use this tool vs alternatives, nor any context about prerequisites or exclusions. The description implies post-generation use but does not explicitly state when it is appropriate.

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