Delimit Prompt Drift

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

Although annotations provide readOnlyHint=false and destructiveHint=false, the description goes beyond them by disclosing that action='record' writes to ai.prompt_drift.record_result, while 'check' and 'rank' are read-only. This is critical operational context an agent cannot derive from the structured fields alone.

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 compact and sectioned for scannability. Every sentence earns its place: purpose, usage, sibling contrast, and side effects are all covered without digression or repetition.

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 tool with six optional parameters, an output schema, and clear annotations, the description provides the essential context: what drift tracking means, when to use it, when not to, how it differs from a related sibling, and which actions have side effects. Nothing critical is missing.

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 100%, so the description does not need to re-explain each parameter. It adds some contextual meaning around the action parameter via side-effect information, but does not materially enrich the semantics of the individual parameters beyond the schema.

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 opens with a specific verb-resource pair: 'Detect prompt drift across Claude / Codex / Gemini for the same task.' It clearly distinguishes itself from delimit_deliberate by noting deliberation is cross-model, whereas this tool tracks single-model drift.

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?

Explicit 'When to use' and 'When NOT to use' sections name the alternative delimit_deliberate and the condition that makes it inappropriate. The sibling contrast reinforces the routing decision with a concrete difference.

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