Execute Tamperbox API code

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

Goes far beyond the annotations: discloses hard limits (64 KiB code, 20 bridge calls, 4 in flight, 15s default timeout, 2 MiB output), sandbox exclusions (no arbitrary URLs, headers, files, imports, process or secrets), data-flow direction (inputs go to Tamperbox; target-check tools may contact the target), and a semantic caveat that JWT decoding does not verify trust. These are exactly the operational traits an agent cannot get from readOnlyHint/openWorldHint.

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-loads the core action and the search-then-call workflow, then groups constraints into a single dense limits sentence. The inline JSON example is verbose but earns its place by showing the exact bridge call shape; overall it is information-dense rather than padded.

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?

An output schema exists, so return values need no prose, and the description still confirms it returns the decoded JSON response body. For a two-parameter sandboxed executor, the behavioral limits, data-flow notes, and example call cover everything an agent needs to invoke it correctly.

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 0%, so the description must compensate. It explains that 'code' is an async function body and mentions a 15-second default that contextualizes timeoutMs against the schema's 30000 max, but it never names timeoutMs explicitly, defines units semantics, or states whether the timeout kills partially collected bridge results.

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?

States a specific verb and resource: 'Run an async JavaScript function body in an isolated runtime,' which is materially clearer than the bare name 'execute.' It implies the relationship to the 'search' sibling ('Search schemas first, then call...') but never names search as an alternative tool, so differentiation is inferred rather than stated.

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?

Gives a concrete workflow: search schemas before calling, then issue a documented request and combine results into JSON. That is clear operating context, but it does not say when NOT to use this tool versus 'search', nor when a plain single API call suffices.

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