Dismiss tasks

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

Annotations only indicate the operation is not read-only and not destructive; the description adds that the effect is a state change that suppresses tasks from the UI. This goes beyond the annotations without contradicting them, though it doesn't discuss reversibility or error behavior.

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?

Single sentence, front-locads the action, and contains no filler or repetition of schema/annotations.

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 a one-parameter mutation with schema coverage and annotations, the description covers the action and its effect. It is slightly light on what happens to invalid or non-terminal tasks, but the tool is simple enough that this is not a major 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 input schema documents that 'tasks' are database IDs, not UUIDs, so format is covered. The description adds the missing semantic filter: the IDs should correspond to finished or failed tasks, which an agent would not know from the schema alone.

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?

Description uses a specific verb ('Mark') and resource ('tasks'), identifies the state transition ('as acknowledged'), and states the observable outcome ('stop showing in UI'). This distinguishes it from sibling task tools like get_active_tasks, list_tasks, and get_task, which are read-only.

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 specifies the conditions for use: only 'finished or failed tasks' should be acknowledged, and the goal is to remove them from the UI. It doesn't explicitly mention when not to use or name alternative tools, but no sibling offers acknowledgment, so the context is sufficiently clear.

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