reconcile_assignment

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

No annotations are provided, so the description carries the full burden. It usefully discloses that the operation is 'read-only with respect to canonical work identity and normative truth' and that it resolves state before effect. But it stops short of clarifying the tool's own side effects (it is a 'reconcile'/'bridge' operation) or its permission/rate/return behavior, leaving meaningful behavioral gaps for a governance-critical tool.

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?

Three dense sentences with little waste, but the front-loaded statement is abstract jargon before concrete information arrives. The elliptical-follow-up detail is useful but the overall prose is heavy and slow to 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?

An output schema exists, so return values need not be explained. However, for a complex governance operation with zero annotations and 0% parameter coverage, the description covers the conceptual 'why' but leaves the two undocumented parameters and the tool's own mutation profile unaddressed.

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 0%, so the description must compensate. It explains only `target` (carrying a resolved value like `MangoMe` without searching historical host memory). The required `request_text` and `workspace_root` are not addressed at all, leaving two of three parameters undocumented in both schema and description.

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 role for the tool ('resolves the managed workspace's canonical restore state and tells the worker which governed transition is appropriate before productive effect'), which is more than a tautology. However, it is wrapped in dense domain jargon ('MangoMe work', 'canonical work identity', 'normative truth') and never cleanly distinguishes itself from sibling tools like prepare_assignment, begin_work, or submit_plan. An agent would struggle to tell precisely what class of action this performs versus its neighbors.

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 implies usage ('The worker may inspect/reason and form a tentative decomposition before this call') and gives a specific case ('For an elliptical follow-up maintenance request, `target` may carry the target already resolved...'). But it never states explicit when-to-use / when-not-to-use or names an alternative sibling, leaving the routing decision to inference.

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