Decide Drift Intent

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

With no annotations provided, the description carries the full behavioral burden and does so: it declares the tool mutating, defines the closing condition (an assertion passing verification at a commit not earlier than the decision), and discloses two distinct failure modes (409 drift_is_defect while the finding stands, 403 escalation without the required policy grant). This is well beyond what the schema conveys.

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 dense but front-loaded: purpose first, then the two outcome branches, then closing/refusal mechanics, then the authorization caveat. Every sentence carries information, though the backtick-heavy jargon and nested parentheticals make it denser than ideal.

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?

An output schema exists, so return values need not be described. For a mutating, policy-gated decision tool with no annotations, the description covers preconditions, the meaning of each branch, the failure codes, and the escalation fallback — nothing an agent needs to call it correctly 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 coverage is already 86%, so the baseline is 3, but the description adds real meaning: it explains the semantics of the two 'intent' values, clarifies that control_id must name the control whose assertions check the behaviour as designed, and implies head_commit is the commit the code was read at. This lifts it above the schema baseline.

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 first sentence names a specific verb (decide) and a specific resource (a description-drift finding), and immediately defines the two possible outcomes ('intended' vs 'defect'). This is a semantically unique action that cannot be confused with siblings like decide_proposal or judge_objective, and it even flags the operation as mutating.

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?

It explicitly states when each outcome applies and what to supply for each: 'intended' means revise the description via create_proposal, 'defect' means name the control in control_id. It also spells out the refusal path (403 with escalation_id unless the delegation policy names drift_intent_decided), tells the agent not to retry, and offers the fallback of raising a drift_intent proposal for a person.

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