delimit_prompt_drift

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

With no annotations provided, the description carries full burden for behavioral disclosure. It does not reveal that the tool has three modes (record, check, rank) defined by the 'action' parameter, nor does it explain side effects like data storage or mutation. The description is vague about what 'detecting' entails.

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 concise at three sentences, with the most important information ('Detect prompt drift') front-loaded. Every sentence adds value, though the third sentence could be considered slightly redundant. Overall well-structured with 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?

Despite having six parameters and no annotations, the description does not explain the different action modes ('record', 'check', 'rank'), which are critical for correct invocation. It also fails to mention that the tool likely stores data for tracking. Missing key behavioral context required for an agent to use it properly.

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%, so the baseline is 3. The description adds no additional meaning beyond the schema. It mentions prompts, models, and task types but does not elaborate on how parameters like 'action', 'success', or 'result_summary' should be used.

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 the tool detects prompt drift, comparing how the same task performs across different models (Claude, Codex, Gemini). It provides a specific verb and resource, but does not explicitly differentiate from sibling tools like delimit_drift_check or delimit_drift_history, leaving some ambiguity.

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 usage for tracking and comparing model performance on tasks, but it does not mention when to avoid this tool or suggest alternatives. No explicit guidance is given for selecting between actions (record, check, rank) or distinguishing from similar drift tools.

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