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

Annotations already cover read-only/idempotent safety, but the description adds substantial behavioral context: relay_bp can stall on degenerate topological errors and reports non-convergence, correlated keeps the second answer only when mechanisms explain it, window requires buffer ≥ (d+1)/2, and outputs are 'sealed'. This is rich beyond the 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?

Front-loaded with the core action and dense but purposeful — nearly every clause conveys a decoder constraint or input expectation. However, the single-paragraph format with semicolon chains is harder to scan than it could be, and 'Sealed with the service's key' is cryptic.

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?

Given 12 parameters, nested objects, and an output schema, the description covers both modes, decoder choices, constraints, and defaults thoroughly. Minor omissions like seed and budget_ns are adequately handled by the 100%-covered 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?

With 100% schema coverage the baseline is 3, but the description goes further by explaining parameter interplay: give code with syndrome or error, memory is {distance, rounds, p}, circuit/model texts are parsed (tags, Pauli-target observables, ^ decompositions), window is {commit, buffer} rounds, and max_weight is for the search decoder.

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 (decode) and resource (syndrome, circuit detectors) and outlines the two operating modes (code capacity vs circuit level) with concrete inputs. It is easy to distinguish from qec_code or qec_threshold without opening another schema.

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?

Provides detailed mapping of which decoder fits which code/input (e.g., union_find for qubits in ≤ two checks, color for colour codes, relay_bp for any code with stall caveat) and describes the required input combinations for each level. No explicit 'when not to use' or sibling comparison, but the internal guidance is strong.

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