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

Annotations already declare readOnlyHint, idempotentHint, closed-world, and non-destructive, so the safety profile is covered. The description adds real value by disclosing the result scope (only models run_simulation has saved a run for) and the return shape, but says nothing about ordering, empty-result behavior, or how saved runs are created.

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?

One sentence, front-loaded with the verb and scope, with the return fields trailing—no filler or restated title boilerplate.

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?

For a zero-parameter read-only lister with full annotation coverage and no output schema, this is nearly complete: scope and return fields are both stated. The only genuine gap is the empty-state/ordering behavior an agent might want before calling.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description does add the useful detail that each result carries an id plus a short description.

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?

Uses a specific verb (List) on a specific resource (sample supply chain models) and narrows scope to those run_simulation has a saved engine run for, which implicitly separates it from list_greenfield_demos and list_opt_demos. It also names the returned fields (id, short description). It stops just short of explicitly contrasting itself with the other list_* siblings.

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 connection to run_simulation implies this is a discovery step before running a simulation, but there is no explicit when-to-use statement, no exclusion of sibling list tools, and no note on what happens when no saved runs exist.

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