async_demo_submit

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

With no annotations, the description carries the full burden and does well: it discloses the non-blocking execution model, the exact return shape ({job_id, status, cache_hit}), and a non-obvious caching behavior (identical (duration_s, value) is a content-hash cache hit with no recompute). It omits failure/timeout or auth characteristics, so not perfect, but rich context is provided.

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 core behavior and the polling guidance in the first two sentences, so the essential contract is read first. The parenthetical meta-commentary about ankusdrive/jobs.py and the 'real FEM/CFD solve' is helpful context but slightly dilutes the core message.

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-required demo tool with no annotations and no output schema, the description covers what it does, how to retrieve results, and what is returned. It is complete on the interaction loop; only the meaning of the 'value' parameter remains 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, and it only partially does. It names both parameters via the cache-key tuple '(duration_s, value)' and implies duration_s is the compute time ('computes for duration_s'), but 'value' is never explained, leaving the semantics of the first parameter undocumented.

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 ('launch a job') plus its defining trait ('runs OFF the MCP channel and return immediately'), which cleanly distinguishes it from synchronous siblings and from job_status/job_result. An agent knows this is the async-launch entry point without opening the schema.

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 says to poll with job_status / job_result, naming the alternatives for the follow-up step, and explains the off-channel rationale (a multi-minute solve never blocks the worker). It doesn't enumerate when to prefer a synchronous solve over this facility, but the async context is clear.

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