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

With no annotations, the description carries the burden of behavioral disclosure. It communicates that the tool performs a state transition and lists role-appropriate actions, but it does not explain side effects, irreversibility, wallet/authentication requirements, or what happens on invalid or disallowed actions. The mention of gas-free terms for pay_job is useful, but broader behavioral implications remain implicit.

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 description is compact and front-loaded: it states the operation first, then organizes actions by role and required params, then gives routing advice. Every sentence adds operational value with no filler.

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 tool with 9 parameters, no annotations, and no output schema, the description covers the role/action matrix well and points to get_job.available_actions as a precondition check. Still, it leaves gaps: no mention of response behavior, error handling, or the refund 'note' parameter, so an agent's end-to-end understanding is not fully complete.

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?

The description adds action-to-parameter mappings that the schema alone does not fully convey, such as deliver(output,message,preview) and quote(price,message). This goes beyond the 78% schema coverage. However, the refund action omits the schema-documented 'note' parameter, so the mapping is not perfectly complete.

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 a specific operation ('Perform one transition') on a specific resource (a job), then enumerates all seller and buyer actions. This clearly distinguishes job_action from siblings like pay_job, get_job, and dispute_action.

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 explicitly separates seller and buyer actions, maps each action to its required parameters, and provides routing guidance: prefer pay_job for paying, and check get_job.available_actions first. This gives the agent actionable when-to-use and when-not-to-use context.

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