task_reconcile

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds the recovery framing and the disposition→effect mapping (requeue / mark failed / reattach with a fresh lease), but does not say what state is permanently lost or that the operation is non-idempotent.

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 tight sentences: the recovery scenario is front-loaded, then the three outcomes. Every clause carries information and nothing is repeated.

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?

Annotations cover safety and there is no output schema to explain, so the burden is on purpose and parameters. Purpose is covered well, but with 6 undocumented parameters and a destructive hint, the description should say more about the error/evidence inputs and irreversibility.

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 0% across six parameters, so the description must carry the load. It clarifies disposition semantics and hints that workerId/workerRole matter for the 'reattach' path, but leaves error, evidence, and id completely unexplained — a significant gap for a destructive mutation.

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 ('Recover a task left interrupted after restart/lease loss') and enumerates the three recovery modes, which lets an agent distinguish it from task_cancel/task_update at a glance. It does not name a sibling alternative, so it stops short of a 5.

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?

Gives a clear triggering condition — the task was interrupted by a restart or lease loss — which is exactly the context that selects this tool over task_heartbeat or task_claim. It offers no explicit when-not-to-use or routing to siblings, so it is clear context but not 5-level guidance.

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