compare_models

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

With no annotations, the description carries the full behavioral burden. It hints at an alignment/validation requirement but never states what happens on mismatched IDs (error vs. silent skip), whether it mutates stored data, or what constraints apply to the optional migration-path and force arrays.

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 sentence is not conciseness here but under-specification: for a 15-parameter tool it omits essentially all necessary context. The one clause present is front-loaded, which is the only structural merit.

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?

Output schema exists, so return values need not be described. However, a 15-parameter, 6-required comparison tool with no annotations and no parameter documentation leaves the agent unable to supply correct arguments or know the failure mode.

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% across 15 parameters, so the description must compensate and largely does not. The phrase 'ordered common-test record IDs' is the only hint that the id arrays must be positionally aligned, and it explains none of the energy, force, or migration-profile parameters.

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 verb 'Compare' and object 'model arrays' give a recognizable action, and the precondition sharpens intent. But it never says which models (dft, mace, runner2, per the 15 params) are being compared or what 'common-test record IDs' are, so an agent cannot distinguish it confidently from the sibling pipeline 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?

The clause 'only when ordered common-test record IDs match' is a gating condition, but no alternative tool is named and no positive when-to-use context is given. An agent is not told what to do if IDs do not match, or what this replaces among run_mace_pipeline/run_runner2_pipeline.

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