badgr_run

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

With no annotations, the description must carry the full burden. It does useful work by disclosing the return fields and the $5/hr hard cap plus a $1/hr human-confirmation gate — meaningful safety context. However it never says whether the call blocks until the job finishes or returns immediately after submission, nor what happens on capacity failure, which is the key behavioral unknown for a job-launch tool.

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 short sentences: what it does, what it returns, what the limits are. Front-loaded and every sentence adds a distinct fact. 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?

No output schema exists, so listing deployment_id/status/receipt_id/logs_url is valuable, and the cost guardrails fill the annotation gap. Missing only the synchronous-vs-asynchronous execution model and what a minimal valid invocation looks like given zero required parameters.

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 100%, so baseline is 3; the description earns a bump by restating the max_price_per_hour ceiling alongside the operational rule that ties it to user confirmation. It does not add meaning for gpu, image, region, or command beyond the schema, but it does link the price cap to behavior rather than just a constraint.

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?

Specific verb and resource: 'Run a one-off GPU job via Badgr'. The word 'one-off' implicitly distinguishes it from badgr_serve (long-running serving), but no sibling is named explicitly. An agent can tell what it does without reading the schema, but must infer the boundary with badgr_serve.

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-off' hints at the exclusion versus persistent serving tools like badgr_serve/deploy_model, but that contrast is never stated. The cost-confirmation rule ('always confirm with the user before running jobs that cost > $1/hr') is a concrete, actionable usage constraint. No explicit when-not guidance or named alternative.

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