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

With no annotations, the description carries the full burden. It does disclose meaningful traits: the work is asynchronous/background, the returned ID is durable, and resubmission is discouraged (implying duplicate submissions are costly or non-idempotent). It says nothing about permissions, rate limits, or cost, and the retry warning hints at a deduplication concern without explaining it, which leaves a real gap for an unannotated mutation-ish 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 short sentences, zero filler, with the core purpose front-loaded and the follow-up routing immediately after. Every sentence carries actionable content.

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?

There is no output schema or annotation coverage, so the description must cover the contract itself; it does so by stating the return is a durable ID and that work_get retrieves the result. Parameters and limits live in the schema, so nothing essential is missing, though failure/retry semantics are only gestured at.

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%, so agent, prompt, and thread are already documented in the schema (including the 8000-byte prompt limit and the default agent). The description adds no additional parameter meaning, 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?

Names a specific action and resource class: starting background (asynchronous) work, and explicitly signals the result is delivered elsewhere (work_get). This clearly separates it from work_get/work_list/work_retry. It does not, however, distinguish itself from the synchronous sibling agent_ask, which is the main ambiguity an agent faces.

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 routes the caller to work_get for results and includes a usage exclusion ('Do not blindly retry submissions'), which is real when-not-to guidance. It stops short of stating when to prefer this over synchronous alternatives such as agent_ask.

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