batch

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

The description discloses critical behavioral details beyond the minimal annotation (readOnlyHint: false). It explains atomic semantics ('atomic: True reverts ALL prior ops on first failure'), the default error handling ('on_error: continue|stop'), and importantly warns that 'execute_code fs side-effects NOT reverted', which is a non-obvious caveat. This equips the agent with necessary operational knowledge.

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 compact and front-loaded with the core purpose, followed by usage guidance and parameter details. It uses a single paragraph with punctuation separating clauses, which is slightly dense. The all-caps 'PREFER' adds assertiveness but reduces readability slightly. Every sentence provides useful information, though formatting could be improved for scanning.

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 and minimal annotations, the description covers the essential command format, error handling, timeout, and atomic failure semantics, plus a side-effect caveat. It does not address the 'validate_aliases' parameter, and the meaning of 'cmd' is somewhat implicit. Overall, it is quite complete for an agent to use safely, but the missing parameter explanation is a notable gap.

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?

Given the schema has 0% description coverage, the description compensates by explaining the format and behavior of 'commands' ('one per line (cmd key=value)'), 'on_error' ('continue|stop'), 'timeout' ('seconds (default 75)'), and 'atomic' (reverts prior ops). However, it does not explain the 'validate_aliases' parameter, leaving one of five parameters without semantic meaning.

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 opens with 'Execute multiple commands in one call', which clearly identifies the tool as a batch execution mechanism. It further specifies the scope as 'reads AND writes' and explicitly positions it against alternatives via 'PREFER over individual tool calls', making its purpose distinct from the many sibling tools.

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 explicitly states 'Use for 2+ ops' as the condition for invoking the tool, and 'PREFER over individual tool calls' guides selection relative to the alternative of calling tools individually. This effectively communicates when the batch tool is appropriate and overrides the default of using single-purpose tools.

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