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

Annotations are all false, providing no positive safety context, and the description does not disclose side effects, reversibility, permissions, or what actually happens to the decision on each transition. It describes the required actions and conditional fields but not the behavioral consequences of performing the transition. There is no contradiction with the annotations.

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?

Three short sentences with no filler. The core verb and resource come first, followed by the necessary conditional logic and a useful legacy-tool consolidation note. Every sentence earns its place.

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 an 8-parameter tool with conditional branching, the description covers the main resolve/supersede branches but omits what 'reopen' entails, why project_id is required, and any side effects or failure modes. The presence of an output schema reduces the need to document return values, but the misleading schema descriptions are not fully compensated.

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 schema descriptions are often generic or misleading: action is described as a 'Usage action or audit-event action filter' and project_id as 'Optional' despite being required. The tool description compensates for the most important parameter by specifying the allowed action values and the conditional requirements for resolution and new_context, plus the optional fields for supersede. However, it still leaves project_id, impact_level, and resolution_note semantically underspecified.

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 and resource, 'Transition a project decision', and enumerates the three allowed actions (resolve, supersede, reopen), making the tool's function clear. It also mentions consolidating the legacy resolve/supersede/reopen_project_decision tools, which clarifies its role as the successor to those. It doesn't explicitly differentiate from current siblings like update_project_todo, but the resource is distinct enough.

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 explicitly states that the tool consolidates the legacy resolve/supersede/reopen_project_decision tools, signaling when to use it instead of those older tools. It also explains action-specific requirements (resolution required for resolve, new_context required for supersede), helping the agent decide which parameters to supply. However, it doesn't contrast with current siblings or state when not to use the tool.

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