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

Annotations already carry readOnlyHint, destructiveHint, openWorldHint, and idempotentHint, so the description only needs to add context beyond them. It does: divergence is framed as a finding rather than an error, trust is defined as agreement between independent readings, and known limitations (small-count mean-field gaps, prior threat-blindness, gated nets with no ODE reading) are named. It does not elaborate on the destructive hint, but the annotations cover that.

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 dense but front-loaded with the core action, and every sentence adds a distinct piece of context: what readings are compared, how to interpret divergence, what trust means, and when readings do not apply. It is long, but the complexity of the tool justifies the length, and there is no filler.

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 comparison tool with no output schema, the description covers the main purpose, interpretation of results, key limitations, and a documentation pointer. The main gap is that it does not specify the exact response shape or what happens when no readings are applicable, but the description is otherwise sufficient for an agent to invoke the tool correctly.

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 input schema already describes all three parameters (id, hours, realizations), with 100% schema description coverage, so the description need not repeat parameter syntax. It adds conceptual context about SSA runs and mean-field gaps, but it does not materially extend the meaning of the parameters beyond what the schema provides; baseline 3 applies.

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: it runs every applicable READING of a model against other readings and reports agreement or divergence. It explicitly enumerates the comparison types (SSA means vs mean-field solve, conservation laws vs simulated means, incidence ranking vs rollouts vs exact search), which distinguishes it from generic sim_compare or sim_verify.

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 gives applicability context, such as game-schema models and the gated-net exclusion, and points to docs/engine-selection.md for the decision procedure. However, it never names sibling tools or states when to choose sim_crosscheck over alternatives like sim_compare, sim_verify, or sim_invariants, so the guidance is implicit rather than explicit.

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