tasks_resume

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

readOnlyHint=true already covers the safety profile, but the description adds the crucial behavioral fact that this is a stub returning a status purely so clients can probe capability without crashing. That is exactly the kind of non-obvious caveat annotations cannot express; it does not, however, cover error behavior or return shape beyond the stub.

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 core sentence is front-loaded and earns its place, and the caveat is essential information. However, the internal developer references ('TODO(B2c)', 'commit 4', 'a future commit') are engineering-notebook noise that the agent does not need and slightly dilute the message.

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, no-output-schema tool whose annotations already signal read-only, the description supplies the decisive context an agent needs: that the operation is currently a no-op probe. Nothing essential is missing, though it could briefly state what the stub status return looks like.

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 description coverage is 100% (the 'id' field is documented as a 16-hex-char task id), so the schema carries parameter semantics. The description adds nothing further about the id, so the baseline 3 applies.

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+resource ('Resume a task') and adds the precondition ('that's awaiting input'), which cleanly separates it from tasks_get, tasks_cancel, and tasks_list. It also discloses that the tool is currently a non-functional stub, so an agent understands both the intent and the present reality.

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?

Explicitly gives the triggering condition (task parked in 'input_required') and, unusually, the when-not: every Task currently succeeds or fails synchronously, so 'resume has nothing to drive.' It stops short of naming sibling alternatives, but the applicability is otherwise unambiguous.

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