design_job_start

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

With no annotations, the description carries the burden and discloses key behavior: it is asynchronous, returns a job id, must be polled, and returns an error for an unknown kind. It does not cover cancellation, concurrency, or job lifetime, but it provides substantial behavioral context.

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 first sentence front-loads the action and return value, and later lines cover timing, polling, arguments, and errors without wasted text. The Returns section is slightly redundant with the output schema, but overall it is well structured.

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?

Given the existing output schema, return values need not be fully explained, yet the description still summarizes them. For an async job-start tool with a free-form params object, it supplies the essential context: timeout rationale, polling workflow, supported kind, and error behavior.

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 0%, so the description must supply semantics; it explains that kind is a registered job kind, names the current route kind, and describes route's required geometry dict plus optional rules/net_classes/grid_pitch_mils. That is strong for params, though future kinds remain open-ended.

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: 'Start a long engine run as a background job; returns its id.' It clearly distinguishes this from design_job_status and design_job_result by naming them as follow-up tools.

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 use it for work that can exceed the MCP tool timeout, such as routing a dense board, and names the exact polling sequence: design_job_status then design_job_result. This gives when-to-use and the correct alternative workflow.

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