aiworkhub_manager_loop_ensure

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

With zero annotations the description carries the full burden and does well: it discloses the write nature ('MANAGER WRITE'), idempotent single-conversation scope ('the repository's one'), synchronous/provider-free execution, the absence of backend/model side effects, and the launching-gate prerequisite. It leaves out failure behavior when the record already exists and any concurrency implications of 'ensure'.

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?

Front-loaded with the operation class and core purpose, then progressively finer detail; every sentence adds information (what it isn't, what it costs, who calls it, what follows). It is dense with internal jargon ('launching gate', 'policy route', 'pins') that will not parse for an uninitiated agent, which costs it a point.

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 zero-parameter tool with an output schema, the description covers purpose, lifecycle position, side effects, and prerequisites — enough to call it correctly. The remaining gap is the ensure/idempotency contract (what happens on repeat calls) and the meaning of the 'launching gate' failure.

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 tool takes no parameters, so the baseline is 4 and there is nothing for the description to compensate for. It correctly describes the implicit input — the repository and launching gate — rather than inventing parameter detail.

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?

Opens with a specific verb+resource ('attach to the repository's one passive manager conversation') and immediately contrasts it with `start` ('no backend is built and no model is called'). An agent can tell it apart from `loop_start`/`loop_new` without opening the schema, though the word 'ensure' itself is never unpacked into its create-if-missing semantics.

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?

States the triggering context plainly ('The panel calls this on open instead of Start') and names the alternative it replaces, plus the follow-on step ('the first ``send`` then pins the policy route'). It stops short of explicit exclusion conditions, e.g. what to call if a conversation already exists or if start was already run.

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