compare

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds meaningful behavioral context: 'Synchronous deterministic compute; nothing is persisted.' This goes beyond annotations by specifying the execution model (synchronous, deterministic) and persistence behavior. It also mentions that runs and seed are forwarded for reproducibility, which is useful. No contradiction with annotations.

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?

The description is three sentences, each earning its place: the first states the core function and output, the second details the winner criterion and per-entry fields, and the third gives the alternative and behavior. Information is front-loaded (main purpose first) with no filler. It is appropriately sized for the tool's complexity.

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 tool with 3 parameters, full schema coverage, and annotations that already cover safety, the description is complete. It explains the output structure (recommended_action, expected_value, probability_of_loss, delta_vs_best), the winner criterion (highest expected value), the request shape (simulate payload), and the usage alternative. There is no output schema, but the description sufficiently describes return fields. Nothing an agent needs to call it correctly 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 description coverage is 100% – all three parameters (runs, seed, scenarios) have descriptions in the schema. The description adds little new parameter meaning beyond reiterating that runs and seed are forwarded and that scenarios use the simulate payload shape, both already stated in the schema. Since the schema already documents parameters well, the baseline of 3 applies; the description doesn't compensate beyond that.

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 opens with a specific verb and resource: 'Run 2-10 named scenarios side by side and return the winner plus each scenario's deltas versus the best one.' It clearly states the output (winner and per-scenario deltas) and distinguishes itself from the sibling recommend by explicitly naming it as the alternative for ranked recommendations. This is precise and unambiguous.

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 description explicitly tells the agent when NOT to use this tool: 'Use recommend for a ranked recommendation over actions instead.' This is a clear exclusion with a named alternative. It also implies the primary use case (comparing 2-10 scenarios) without leaving the decision to inference. The guidance is direct and actionable.

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