job.submit

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

Annotations are all false, so the description carries more burden, but it adds only 'Risk: standard; maturity: L3' and a policy note. It does not disclose that this is a mutating, non-idempotent operation (despite annotations indicating this), whether jobs execute asynchronously, whether a jobId is required for later status/cancel calls, or what side effects occur. No contradiction with annotations exists, but the behavioral disclosure is minimal.

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?

The text is short, but this is under-specification rather than conciseness. The only informational content is a risk/maturity label and a policy reminder, neither of which earns its place toward helping an agent invoke the tool. There is no front-loaded functional statement, so the brevity adds no value.

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 job-submission tool with 8 parameters, a nested object, enum-constrained fields, and a required transaction id, the description is woefully incomplete. It does not explain the job lifecycle (submit → status → cancel), the relationship to blender_transaction_begin/commit, or how output schema results map to jobId. Despite an output schema existing, the agent cannot determine the tool's role or correct invocation from this description.

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 50%, which is low, and the description contains no parameter information at all. The core parameters 'kind' and 'format' have enums but no descriptions, and the description does not explain what job types or export formats are valid, nor how the 'parameters' object should be structured. The description fails to compensate for the schema's incomplete coverage.

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 is purely tautological: it states that the tool is the 'PartMe Blender Harness command job.submit', which merely restates the title. No verb, action, or resource is given, and it does not say what submitting a job actually does (e.g., queue execution, start a render, export). It is also indistinguishable from sibling job tools like blender_job_cancel or blender_job_status without reading their schemas.

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?

The description provides no guidance on when to use this tool versus alternatives. The only additional sentence, 'Requirements: Per-request argument checks and session policy still apply', is a policy note rather than usage context. There is no mention of prerequisites such as an active transaction, which the required _transactionId parameter implies.

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