Run a functional check in isolation

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

Substantially exceeds the annotations: it discloses disposable-copy isolation, network blocking, that writes are confined to the copy, the exit-code-zero rule for VERIFIED, pipefail injection for bash, and the INCONCLUSIVE fallback when the sandbox cannot start. This also explains why readOnlyHint=true holds despite commands that write files, which is genuinely additive 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?

Front-loaded with the core action and scope, then progressively narrower operational caveats in four tight sentences with no filler. Each sentence carries distinct information (isolation, shell recipe, file placement, failure mode).

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 5-parameter tool with no output schema, it covers the important unknowns: isolation, network policy, success criterion, and one failure terminal state. It does not enumerate the full result vocabulary beyond VERIFIED/INCONCLUSIVE, which is the only remaining gap an agent might hit when interpreting output.

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, but the description adds real meaning beyond the schema: the bash + ["-c", "..."] pattern for pipelines (the schema only says 'No shell is used'), and the constraint that every needed file must live in the repository, which implicitly scopes path. It says nothing about claim or timeout_ms, leaving those to the schema.

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 first sentence states a specific verb and execution context: run a command and arguments in a disposable repository copy under the host OS sandbox. It is far more precise than the title alone and makes clear this is a functional-check executor rather than a metadata/URL/npm verifier. It never names the sibling verifiers (verify_changes, verify_npm, verify_url) it is distinguished from, so it stops short of a 5.

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?

Usage is implied by the constraints: it explains the shell-pipeline recipe (command bash, args ["-c", "..."]) and warns that files outside the repository do not exist in the sandbox. There is no explicit 'use this instead of verify_changes/verify_npm when...' routing, and no stated exclusions, so the agent must infer when to reach for this tool versus its siblings.

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