get_assembly_job

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

With no annotations, the description carries the full behavioral burden and does a good job: it discloses the outcome_unknown token and its meaning (GUI exceeded dispatch budget, job may still finish), an idempotency/safety rule (do not re-issue the mutation), and a result-retention policy (until history eviction at 32 completed jobs or FreeCAD exit). It stops short of saying whether the poll itself has side effects or cost, and it never mentions include_result.

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, front-loaded segments with no filler: the core action first, then the outcome_unknown caveat, then the retention note. The sentence fragments ('Poll without waiting for the GUI') are slightly clipped but each line earns its place.

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, so the description must cover return semantics, and it partly does (durable outcome, PNGs, outcome_unknown). But for a 2-parameter poll tool it leaves include_result entirely unexplained and does not describe the shape of a non-final response, which is the thing an agent will most often receive.

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% and the description never names job_id or include_result. The phrase 'Includes durable outcome and native PNGs when done' hints at what the result payload contains, but it does not tell the agent that include_result toggles that payload, nor what job_id format/lifetime is expected. Two undocumented parameters at 0% coverage with no compensating text is a clear gap.

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 the action ('Poll without waiting for the GUI') and what the tool yields ('durable outcome and native PNGs when done'), which makes it readable as a job-status poll for an assembly job. It does not explicitly name the resource (job) or distinguish itself from siblings like get_rpc_status or get_async_status, so a 4 rather than 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?

It gives a concrete usage rule for the ambiguous case: on outcome_unknown, 'continue polling; do not duplicate the mutation.' That is exactly the guidance an agent needs and it is stated explicitly. It does not, however, contrast this tool with alternative status tools (get_async_status, get_rpc_status), so the alternative-selection dimension is left implicit.

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