cli_batch

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

With no annotations, the description carries the full burden and only discloses the stop-on-error control flow. It never mentions the `allow_unsafe` gate that governs whether arbitrary commands are permitted, the `save` persistence side effect on the project, per-command timeout limits, or whether partial batches leave the project partially mutated.

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?

Two short sentences, zero filler: the execution behavior is front-loaded and the use case follows immediately. Nothing is repeated or padded.

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?

A six-parameter command executor with no annotations and no output schema is a high-risk, high-ambiguity tool, yet the description says nothing about safety gating, state persistence, per-command timeouts, or what is returned. The agent is left to infer side effects from the schema alone.

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 every parameter is already documented and the description adds nothing beyond repeating `continue_on_error` semantics. Baseline 3 applies since 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?

Specific verb+resource ('Run several CLI commands in order') with a stated execution semantics (stop at first KO). It anchors itself to a sibling producer (`project_export_script`) to explain the intended input, though it never contrasts directly with the single-command `cli` sibling an agent could confuse it with.

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?

Gives one concrete use case — replaying `project_export_script` output — which implies when to reach for it. But there is no explicit when-not, no steering toward `cli` for single commands, and no mention of prerequisites such as login or an open project.

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