list_qldpc_codesReturn the catalog of supported qLDPC codes (id, label, family, n, k, d, circuitLevelDistance, ancilla counts, roundsPerLogicalOp, threshold, prefactor [per block per syndrome cycle], logicalErrorExponent [= d_circ/2], source URLs). Use a code's id as the errorCorrectionCode input to compute_expectation.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful detail about the returned fields and the logicalErrorExponent formula, while containing no contradictions or hidden side effects.
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 a single dense, well-structured sentence followed by a clear actionable instruction. All clauses earn their place by defining the catalog scope, listing output fields, and linking to the next tool.
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?
There is no output schema, but the description fully specifies the output contents including field details and formula relationships. For a zero-parameter read-only catalog function, this is a complete and unambiguous definition.
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 tool has zero parameters, so the description does not need to explain any parameter syntax. It still adds value by explaining that the `id` field is intended to be passed into compute_expectation as `errorCorrectionCode`.
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?
Starts with 'Return the catalog of supported qLDPC codes' and then enumerates the exact contents (id, label, family, n, k, d, threshold, etc.). This is a specific verb+resource that is clearly distinguishable from sibling tools such as list_example_algorithms or list_quantum_computers.
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 a concrete downstream usage: 'Use a code's `id` as the `errorCorrectionCode` input to `compute_expectation`.' This clarifies how the catalog output should be consumed, though it does not explicitly state when not to use it or compare against alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool has a clearly distinct role: compute_expectation and compute_required_error_rate are forward/inverse pairs, compare_hardware_scenarios is a batch wrapper for compute_expectation, and the list_* and get_* tools each target a different data category (hardware, timing, historic, examples, codes). The fit_historic_series tool is distinct from get_historic_series (analysis vs. retrieval). No two tools appear ambiguous.
All tool names follow a strict lower_snake_case verb_noun pattern: compute_*, get_*, list_*, fit_*, compare_*. The verbs precisely indicate the action (computation, retrieval, fitting, comparison) and are used consistently across the set.
With 12 tools, the server is well within the ideal 3-15 range. Each tool serves a distinct purpose in the quantum resource estimation workflow: data listing, forward/inverse expectation calculations, fault-tolerant resource estimation, rate computation, historic analysis, and context retrieval. No tool feels redundant or unnecessary.
The tool surface comprehensively covers the domain: current hardware data (list_current_quantum_computers, list_hardware_timings), historical trends (get_historic_series, fit_historic_series), algorithm resource examples (list_example_algorithms), error correction codes (list_qldpc_codes), forward and inverse error calculations (compute_expectation, compute_required_error_rate), batch comparison (compare_hardware_scenarios), deep resource estimation (compute_fault_tolerant_resources), a throughput metric (compute_quantum_volume_rate), and the agent brief. There are no obvious missing operations for the stated purpose.