Update Project Decision

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

Annotations already communicate readOnlyHint=false, destructiveHint=false, and idempotentHit=false. The description adds meaningful behavioral context by detailing transition semantics and required parameters for each action. It does not disclose potential side effects or authorization requirements, but it does not contradict 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?

The description is three sentences, front-loaded with the core verb and resource, and each sentence adds essential information: purpose, action variations, required parameters, and consolidation note. There is no filler or redundancy.

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?

The description covers the action-specific requirements well, and an output schema exists so return values need not be explained. However, it does not clarify the roles of the required decision_id and project_id, and it leaves unresolved the schema's misleading project_id description (marked optional but required). For a complex 8-parameter tool, this is a minor but notable gap.

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 tool description provides critical conditional parameter semantics that are not present in the schema: it enumerates allowed action values and specifies which parameters are required for each action. This goes well beyond the generic schema descriptions (e.g., action is described as 'Usage action or audit-event action filter'), making the actual invocation logic clear.

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 'Transition a project decision' and immediately specifies the three allowed actions (resolve, supersede, reopen), clearly defining the tool's scope. The closing note about consolidating legacy tools distinguishes it from previous separate tools, so purpose is unambiguous.

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 each action is appropriate via action-specific requirement notes ('resolution is required for action=resolve', 'new_context ... required for action=supersede'), and the consolidation note explicitly tells the agent this tool replaces the legacy resolve/supersede/reopen_project_decision tools. It does not compare with unrelated sibling tools, but the guidance is clear.

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