tasks_refresh

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: this is the explicit write action, it performs process reaping and lazy child CID linking, and other surfaces only expose the persisted cache. Idempotency is only implied by the annotations, not expanded on.

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?

Two short sentences, with the action front-loaded and the read-only contrast as follow-up. No wasted filler; the only mild cost is unexplained internal shorthand ('CID', 'process reaping') that an outside agent may not parse.

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?

With no parameters and an output schema present, the description need not explain return values, and it does cover what the tool changes and how it relates to the read-only surface. What is missing is a note on cost or side effects of triggering reaping, which would round it out.

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?

There are zero parameters with 100% schema description coverage, so the schema fully carries parameter semantics and the baseline of 4 applies. Nothing in the description is needed to compensate.

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 states a specific verb and resource: 'Reconcile tracked task lifecycle and spawned-session links', which an agent can distinguish from the read-only 'tasks' sibling. The second sentence sharpens what it actually does (process reaping, lazy child CID linking). It stops short of a crisp one-line definition, leaning on internal jargon, but the purpose is recoverable.

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 contrasts itself against alternatives: read-only task/status surfaces 'only show the persisted cache', implying you call tasks_refresh when you need the cache reconciled against live state. That is a clear selection cue, though it never explicitly says when NOT to call it or names a sibling by name.

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