blockrun_modal

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

Annotations already indicate this is a mutating, open-world, destructive tool. The description adds crucial behavioral context beyond annotations: timeout is the billed lifetime, charged upfront with no refunds, sandboxes terminate on timeout/budget reset, and GPU access is capped at H100. This is fully consistent with readOnlyHint=false and destructiveHint=true.

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?

Despite being long, the description is front-loaded with purpose and usage guidance, then uses compact bullet lists for pricing and endpoint schemas. Every sentence earns its place, espacially the billing warning, which is essential for correct invocaation and cost awareness.

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 multi-endpoint, high-stakes billing tool with no output schema, the description is nearly complete: it covers paths, request bodies, pricing, GPU limitations, termination behavior, and budget replan. The main gap is that it never explicitly states what responses look like, e.g., that sandbox/create returns a sandbox_id needed for subsequent calls, though the endpoint list implies this chaining.

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 schema only describes 'body' as a JSON POST body, so the description adds real semantic value by specifying per-endpoint body shapes such as { image?, timeout, cpu?, memory?, gpu?, setup_commands? } for sandbox/create and { sandbox_id, command, timeout? } for sandbox/exec. It also clarifies path examples and the billing meaning of timeout, going well beyond the thin schema descriptions.

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 opens with a specific verb and resource: 'Run isolated code in a BlockRun-hosted Modal sandbox — disposable remote container, optional GPU.' It then lists concrete endpoints under /v1/modal/, making the tool's scope unmistakable and clearly distinct from sibling tools like blockrun_image or blockrun_chat.

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?

It explicitly states when to use the tool ('clean ephemeral environment', 'GPU access', 'safer place for untrusted code') and when not to ('Prefer local tools for normal repo work'). It also enumerates the available POST paths, helping the agent choose the right operation within the tool.

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