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

With no annotations, the description carries the full burden and does disclose real behavior: it returns stdout, stderr, and exit code, defaults to a 5-second timeout, and background mode yields a job ID. It omits safety-relevant context such as sandboxing, working directory, and side effects, which matters for arbitrary command execution.

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 core purpose and return contract are front-loaded in the first two lines, with secondary detail in a bulleted tips block. It is reasonably tight, though the shell-usage tips verge on filler for an agent that already knows bash.

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 must cover returns — and it does, naming stdout, stderr, and exit code, plus the background job-ID pattern. It is nearly complete for this tool, with only timeout-failure behavior and environment/permission scope left unspecified.

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 100%, so the schema already documents command, background, and timeout_ms. The description restates the default timeout and background job-ID behavior without adding syntax or format detail, matching the baseline of 3 when the schema does the heavy lifting.

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 opening line 'Run a command in bash' is a specific verb+resource and is unambiguous, and the description correctly identifies the companion tool for background jobs. It falls just short of 5 because it names that sibling as 'get_status' while the actual sibling is 'get_job_status', slightly blurring the routing.

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 gives clear conditional guidance: use background mode when a command takes more than a few seconds, and use get_status to poll a backgrounded job. It stops short of explicit when-not-to-use guidance, and the find/grep and mv/rm/mkdir tips are shell advice rather than tool-selection guidance.

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

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

With no annotations, the description carries the full behavioral burden and does meaningful work: it discloses the return payload shape (stdout/stderr so far, exit code null while running, running flag) and, critically, that completed jobs are cleaned up after their status is read — a side effect an agent must know before calling. It omits error behavior for unknown/expired IDs and any rate/polling constraints.

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, zero filler, with the core purpose front-loaded and the cleanup caveat placed last where it reads as an important aside rather than burying the primary action.

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, so the description must explain return values, and it does so concisely and accurately. The remaining gap is operational: no guidance on polling cadence, timeout/waiting behavior, or what happens when the job ID is unknown or already cleaned up.

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 100% and the single `jobId` parameter is fully documented in the schema, including that it comes from `execute` with `background: true`. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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+resource: 'Check status of a background job', with a clear object (job status) that is distinct from the sibling `execute`. However, the description never names `execute` or explicitly ties itself to jobs launched with `background: true`, so the sibling relationship is only inferable from the schema's param description.

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 rather than stated: an agent can infer this is used after starting a background job via `execute`, but there is no explicit when-to-use, when-not-to-use, or polling guidance. No alternatives are named or excluded.

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