shell_exec

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

No annotations are provided, so the description carries the full burden. It does not disclose that commands may mutate state, that the shell persists between calls, how output is returned, or that errors can occur mid-command. 'Execute one bash command' only states the action, not the behavioral consequences.

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 a single concise sentence with no fluff or redundant detail, and it is front-loaded with the core action. It is under-specified overall, but as far as conciseness alone it earns high marks.

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?

Given that this is a shell execution tool with potentially destructive side effects, no annotations, and five parameters, the description is too thin. It omits prerequisites (an existing shell), behavioral guarantees, and guidance around the timeout/output parameters. The presence of an output schema reduces the need to describe return values, but not these other aspects.

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%, and the description adds no parameter-level meaning beyond the raw property names. It does not clarify shell_id's relationship to an existing session, or the meaning of yield_ms, timeout_ms, or max_output_bytes. With zero schema coverage, this is insufficient.

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 uses a specific verb 'Execute' and names both the resource ('one bash command') and the context ('persistent shell'). This clearly distinguishes it from sibling tools like shell_open, shell_write, and shell_read, which have different purposes.

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?

The description gives no guidance on when to use this tool versus shell_write or shell_read, and no mention that shell_id must already exist (e.g., from shell_open). Usage context is only implied by the word 'Execute.'

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