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

With no annotations provided, the description carries the full burden and does so well: it discloses that state (files, installed packages, running processes) survives between calls and across days, the auto-pause/resume behavior, quota limits (3 sandboxes, 60 run-minutes/day), and the secrets isolation guarantee. It omits what kill does to persisted state and what happens when quotas are exhausted.

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?

The description is dense and front-loads identity before enumerating actions, lifecycle, and quota, so the most decision-relevant facts come first. It is long and reads as a run-on list of actions, but nearly every clause carries information the schema does not.

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?

There is no output schema and no annotations, so the description should arguably explain what run/status/list return (stdout, exit code, sandbox state), which it does not. For a 13-parameter tool this leaves a real gap, though the action coverage and persistence/secret semantics are otherwise solid.

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 only 8% (just the secrets field), so the description must compensate and largely does, mapping cmd/cwd/timeout_s/background to run, path+content/content_base64 to write_file/read_file, and ns/prefix/dir to the sync actions. The notably absent piece is the `name` parameter, which selects which sandbox is targeted and is never explained.

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 states a specific resource (a named Linux sandbox with Python, Node, shell, internet) and enumerates the exact actions it supports, so an agent can tell immediately this is the code-execution tool and not a sibling like ai, browser, or fetch. It also distinguishes itself by the persistence model ('pauses instead of dying').

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 through the action list and the store-sync coupling ('sync_from_store... copy your stored files in'), and lifecycle facts (created on first use, auto-pause, ~1s resume) inform when it is cheap to call. However, there is no explicit 'use this when you need X instead of Y' framing against siblings, so guidance remains inferential.

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