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

The description adds substantial behavior beyond the annotations: it discloses the Monte Carlo sampling method, the requirement for a continuous engine, the refusal behavior with a reason, and the Pareto-flag output. While it does not elaborate on what destructive side effects might occur (destructiveHint=true), annotations already flag that trait, so the description adds useful context without contradiction.

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 focused sentences pack all critical information: the first sentence explains the method and output, the second states the limitation and redirects. No filler; every phrase earns its place.

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 complex tool with no output schema, the description adequately explains what is returned ('every sample with a Pareto flag', 'non-dominated set is the trade-off frontier') and when it fails. It could mention side effects or result format more fully, but it covers the essential operational and limitation aspects.

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?

With 100% schema description coverage, the baseline is 3, but the description enriches the parameters by mapping 'transition rates' to the parameters JSON, 'served vs walked out' to objectives, and 'Monte Carlo samples'/'horizon' to samples/hours. This gives the agent domain-level understanding beyond the schema field 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?

The description states a specific resource ('transition rates for a stored model') and a specific algorithm ('Multi-objective optimisation', 'Monte Carlo samples', 'Pareto flag'), and it explicitly names a sibling tool (sim_compare) when the model has a schedule or gate. This differentiates it clearly from other sim_* 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 gives an explicit exclusion condition ('a model with a schedule or a gate is refused') and directly points to the alternative ('use sim_compare with explicit scenarios for those'). This is precise when-to-use / when-not-to-use guidance that an agent can act on.

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