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

Annotations only flag it as a non-readonly, non-destructive, closed-world mutation. The description adds critical behavior beyond that: hard prerequisites that cause failure, the auto-creation-plus-activation side effect, and the returned process ID. These are exactly the traits an agent cannot infer from the structured fields.

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-loaded with the core action and return value, then structured into prerequisites and two modes with a labeled list. Slightly long, but every section (prerequisites, both modes, the repeated runs warning) carries actionable weight.

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 12-param, no-output-schema tool this is thorough: it covers the return value, the failure prerequisites, and the two invocation modes. It omits guidance on the more advanced parameters (variantCount, simulationType, customVariants, personaIds), though those are fully described in the schema.

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 100%, so the schema already documents each parameter; baseline would be 3. The description adds genuine conditional meaning by explaining the agentId-vs-prompt branching and which fields are required for each path, which the schema alone does not express.

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 precise verb+resource ('Start a new optimization process for an agent') and the return value ('Returns the optimization process ID'). It is clearly distinguishable from siblings like validate_variant, apply_variant, stop_optimization, and list_optimizations.

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?

Explicitly enumerates when the tool will work and when it will fail ('optimization will fail without these'), names the required sibling tools (create_run, sync_context_from_url, update_settings), and lays out the two invocation paths (existing agentId vs auto-create with prompt+agentName+llmModel).

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