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

Adds meaningful behavior beyond annotations: it runs immediately, acts as the person, and the recorded reason steers agents not to raise the same item again soon. Annotations already cover destructiveness and idempotency, so this is strong supplemental context.

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?

Front-loads the action and follows with the reason options, the downstream effect, and how to obtain the actionId. Every sentence contributes useful context with no filler.

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?

Complete enough for a destructive mutation: it identifies the task source, immediate execution, acting identity, and future suppression effect. It could say more about reversibility or undo, but annotations and the sibling undoAction help cover that.

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 100%, so the schema already documents actionId, reason, and workspaceId. The description mainly repeats the reason enum values and points to readWaitingItems for actionId, without adding much semantic depth beyond the schema.

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?

States a specific verb and resource: declining one waiting task on Tasks. It clearly distinguishes the action from readWaitingItems, which lists the cards, and implies the opposite of approveItem.

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?

Explains that this is for declining one waiting task and that readWaitingItems supplies the actionId. It gives clear usage context but does not explicitly compare against approveItem or undoAction.

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