run_workload

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

With no annotations, the description carries the full burden and does reasonably well: it declares the return fields (deployment_id, status, receipt_id, logs_url), a hard spend cap, and a user-confirmation gate for costly jobs. It omits lifecycle behavior an agent would want — whether the job is billed until stopped, how to terminate it (presumably badgr_down), and whether the call blocks or returns immediately.

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 tight sentences: capability and return values first, then the hard limit, then the confirmation rule. Nothing is wasted and the most decision-relevant constraint is front-loaded.

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-annotation, zero-output-schema job launcher, the description covers what the tool does, what it returns, and the cost guardrails. The remaining gap is post-launch lifecycle and cancellation guidance, which matters for a billable GPU job but is a single missing piece rather than a systemic hole.

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 100%, so all seven parameters are documented in the schema itself, making 3 the baseline. The description only restates the $5/hr ceiling already encoded as the schema maximum, adding no syntax, units, or interaction detail beyond structured data.

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?

Names a specific verb and resource ('Run a one-off GPU job via Badgr') and the word 'one-off' implicitly separates it from persistent-serving siblings like badgr_serve. However, it never distinguishes itself from the confusingly similar sibling badgr_run or from deploy_model, which an agent would need in order to choose correctly.

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?

One concrete operational rule is given ('Always confirm with the user before running jobs that cost > $1/hr'), which is genuinely useful gating behavior. But there is no explicit statement of when to prefer badgr_run, badgr_serve, or deploy_model, so the usage boundary is only implied by 'one-off'.

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