Record a drift score

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

The description adds context beyond annotations by disclosing upsert behavior and the derived verdict logic. Annotations already note non-readOnly and non-destructive, and the description aligns with these without contradiction.

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 three sentences with no wasted words. The first sentence front-loads the core action and verdict logic, the second covers gap and files, and the third states the upsert behavior. Everything is essential.

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?

Given 7 parameters and no output schema, the description covers the essential behavior (recording, verdict, gap/files, upsert). It does not explain return values or error states, but this is acceptable for a recording tool. The description is fairly complete for the tool's purpose.

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?

The description explains the meaning of key parameters (score range, derived verdict, gap for shortfall, optional files) and the upsert behavior, adding value beyond the schema's property descriptions. Schema coverage is 57%, and the description compensates for the less-documented parameters like project and ticket.

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 records a 0–100 fidelity score for one ticket in a drift run, explaining the derived verdict logic and optional override. It specifies the resource (ticket in drift run) and verb (record), distinguishing it from siblings like drift_report or drift_start.

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 explains when to use this tool (to record a score per ticket) but does not explicitly state when not to use it or mention alternatives. However, the context of recording a single score is clear, and the sibling list provides implicit differentiation.

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