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

Annotations cover the safety profile (destructive, non-idempotent, open-world), and the description adds genuinely non-obvious behavior: token cost per 50 samples, refusal conditions with reason, non-negative rate-range constraint, and that every sample is returned with a Pareto flag. It stops short of explaining what the destructiveHint actually means (whether runs persist artifacts), which is the remaining gap.

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?

Front-loads the core operation, then cost and refusal rules in order of decision relevance. The parenthetical example and cost sentence are dense but each earns its place; slightly crowded overall.

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 6-parameter tool with no output schema, the description supplies what the schema cannot: return content (all samples with Pareto flags), cost model, refusal semantics, and the routing fallback. Nothing essential for a correct call is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: the non-negativity rule for rate ranges, the purpose of the horizon and sampling loop, and the interpretation of objectives for the caller. It does not re-specify defaults or bounds already in the schema.

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?

States a specific verb+resource ('multi-objective optimisation over transition rates for a stored model') and elaborates the mechanism (Monte Carlo sampling, horizon runs on the continuous engine, Pareto flagging). It also names the sibling it is not (sim_compare) for models it refuses.

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 the when (trade-off frontier over rate ranges, with a concrete example: 'which staffing is non-dominated on served vs walked out'), the when-not (models with a schedule or a gate are refused), and the alternative (use sim_compare with explicit scenarios).

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