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

Goes well beyond the annotations by disclosing billing (0.1 credit/minute, 0.1 minimum per command), that the timeout is held as credits up front, that long runs flip to an async task_id after roughly 50 s, and that files written persist to the project. These are behavioral traits the destructiveHint/readOnlyHint annotations cannot convey.

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 tight sentences, front-loaded with the core action and sandbox constraints, with cost and return behavior following logically. Nothing is redundant and every clause carries information.

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?

With no output schema, the description correctly explains the return contract ('output, or a task_id'), which is exactly what an agent needs. The only gap is that it doesn't point to composer_task_status for retrieving async results, a minor omission for a tool that can return early.

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 the baseline is 3, but the description adds meaning the schema does not: the ~50 s threshold explains when the async task_id path (and thus the timeout parameter's practical effect) kicks in, and the credit billing clarifies the cost of longer timeouts. Command and project_id get no extra explanation, hence not a 5.

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 ('Runs a shell command in the project's network-isolated sandbox') and enumerates the in-sandbox tooling, which cleanly separates it from siblings like composer_edit_file, composer_write_file, and composer_read_file. An agent can identify the tool's scope without inspecting the schema.

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 establishes context (network-isolated sandbox, no network, files saved to the project) that implies when the tool is appropriate, but never states when to prefer it over composer_read_file/composer_write_file or how to follow up on a returned task_id. Usage is inferable rather than explicit.

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