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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), yet the description adds real substance: the fitted model P(d) = a·(p/p*)^((d+1)/2), the per-point return contents (shots, failures, rate, standard error), the meaning of below_threshold, and that results are cryptographically sealed. The caution about crossings on few shots is genuinely useful behavioral context.

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 purpose and structured by family/decoder branches, with the interpretation warning placed last where it belongs. The middle sentence is heavily compressed with formula and jargon, but each clause carries information rather than 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 simulation tool with 7 parameters and four families, the description covers what is computed, the model fitted, and how to read the output, and an output schema already exists so return shapes needn't be spelled out. Only the seed/determinism story and cost/runtime expectations are 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 high (86%), so the baseline is 3; the description goes beyond it by tying decoder and rounds to the surface family only and by stating the per-round model those parameters feed. It still leaves 'seed' and the interaction between p array length and shots unaddressed.

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 and resource ('Measure logical failure rates over distances and physical error rates') and scopes it to threshold-style sweeps, which separates it in spirit from the code/decode siblings. It never names qec_code or qec_decode, so the differentiation is inferable rather than explicit.

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 explains which family/decoder combination to pick for a given study ('surface at circuit level ... or color, toric or surface_capacity at code capacity'), which is parameter-level guidance. It gives no tool-level when-to-use/when-not guidance versus qec_code or qec_decode, leaving that to inference.

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