Record a drift score

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

Beyond annotations, the description adds that the tool upserts by ticket and derives verdicts automatically unless overridden. However, it does not disclose potential side effects, permission requirements, or error handling for write operations.

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 efficient sentences with key information front-loaded. No unnecessary words, but could be slightly more structured (e.g., bullet points for parameters).

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?

Covers the recording action and optional inputs but lacks guidance on how this tool fits with sibling tools (drift_report, drift_remediate) and does not describe return behavior or error states. Adequate for a straightforward tool but could be more comprehensive.

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?

Adds meaning for the gap and files parameters beyond the schema by describing their purpose. With 57% schema coverage, the description partially compensates but does not cover the semantics of ticket, project, or verdict parameters.

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?

Clearly states the tool records a fidelity score for a single ticket in a drift run, with explicit verb and resource. Distinguishes from siblings like drift_start and drift_report by focusing on per-ticket scoring.

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?

Implies usage context (within a drift run, per ticket) and mentions upsert behavior, but does not explicitly state when to use this tool vs alternatives like drift_report or drift_remediate. No exclusion criteria.

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