run_mace_pipeline

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

With no annotations, the description carries the full burden, and it does disclose a meaningful trait: fail-closed semantics and that MACE is never launched. However, it does not say what happens if execute=true or dry_run=false, whether any filesystem writes occur, or what auth/environment requirements exist for the python_executable path.

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?

A single tight sentence with the key constraint front-loaded and zero filler. It is arguably over-concise rather than wasteful, but nothing in it is expendable.

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?

An output schema exists so return values need not be described, but a 7-parameter mutation-adjacent tool with no annotations and no parameter documentation leaves the agent materially under-informed about invocation and side effects.

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?

Seven parameters with 0% schema description coverage and the description explains none of them. Fields like mode, seed, python_executable, and the dry_run/execute pair are left with no meaning, types, or allowed values beyond their bare names.

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?

Names a specific verb ('Return') and resource ('MACE dry-run plan'), and the phrase 'never launches MACE' distinguishes it from the execution-oriented siblings run_runner2_pipeline and get_pipeline_status. It falls short of 5 because 'MACE' is never defined and the dry-run only framing leaves the role of the execute/dry_run parameters ambiguous.

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?

No when-to-use guidance, no conditions, and no named alternatives despite seven sibling tools covering pipeline status, DFT dataset work, and a second pipeline runner. The agent must infer selection criteria entirely on its own.

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