Quantum Expectations

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds useful behavioral detail beyond annotations: the single-call batching against multiple hardware entries and the default-to-all-hardware behavior when hardwareIds is omitted. It does not describe the return format, but that is more a completeness gap than a transparency one.

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?

Two sentences with no filler. The primary purpose and the key usage condition are front-loaded, and the hardwareIds default is stated compactly in the second sentence.

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?

The description gives solid selection guidance and the default hardware behavior, but there is no output schema and the description never says what the returned comparison data looks like. For ranking platforms, an agent would benefit from knowing whether results include expectation values, error rates, or other metrics. Overall adequate for choosing the tool, but not fully complete for invoking it confidently.

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 description adds almost no parameter-level meaning beyond the schema. The hardwareIds default is already documented in the schema, and the description does not clarify numQubits, compDepth, useErrorCorrection, or the error-correction code interactions. With schema description coverage at only 50%, the description should compensate but does not.

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 clearly states the tool runs the same circuit against multiple hardware entries in one call, which distinguishes it from sibling tools like compute_expectation and list_current_quantum_computers. The verb 'compare' plus the batching behavior make the purpose immediately clear.

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 frames this as the tool to use when an agent wants to rank platforms without making N sequential compute_expectation calls. It also explains the default behavior when hardwareIds is omitted, giving an agent a clear selection and invocation rule.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds valuable behavioral context: the response is self-describing (formulas, assumptions, caveats, glossary, SOTA hardware, historic series with URLs), and it discloses the routingOverheadFactor for 2d-lattice connectivity in the no-EC path. This goes beyond annotations to inform the agent about output richness and calculation specifics.

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 well-structured paragraph that front-loads the core purpose, then adds essential behavioral details and sibling pointers. Every sentence earns its place: no fluff, no redundancy. It is concise given 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?

Despite no output schema, the description explicitly states what the response contains (effective error rate, success probability, overhead, self-describing context). It covers input relationships, error correction optionality, and routing behavior. For a 9-parameter tool with 2 required and enums, this is remarkably complete.

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 67% (some params have descriptions, but numQubits and compDepth lack them). The description compensates by naming them as 'qubit count n, depth d', and clarifies the relationship between hardwareId and qubitErrorRate (exactly one supplied), connectivity defaults, and the routing multiplier effect. It adds meaning beyond the schema for key parameters, though it doesn't detail every param individually.

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 states a specific verb ('compute') and resource ('effective error rate, success probability, and optional overhead') for a quantum circuit. It explicitly differentiates from siblings by naming compute_required_error_rate for the inverse and compare_hardware_scenarios for ranking, leaving no ambiguity about scope.

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?

It clearly explains when to use this tool: given a circuit with error rate, qubit count, depth, and connectivity. It also gives explicit alternatives: use compute_required_error_rate for the inverse question and compare_hardware_scenarios to rank platforms. The routing overhead behavior and hardwareId default are stated, giving agents a full usage picture.

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

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

Annotations already declare read-only, idempotent, and non-destructive traits. The description adds meaningful behavioral context: it always reports results under two logical-error fits (conservative and optimistic) because they differ by 13–268x, returns an explicit infeasible block when no factory/distrance satisfies the budget, and clarifies that it does not make quantum-vs-classical conclusions. This goes well beyond the annotations and provides important invocation expectations.

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 carrying essential information: the first establishes the model and outputs, the second highlights the dual-fit reporting and its significance, and the third defines the infeasible case and scope boundary. It is front-loaded with the main purpose and efficiently conveys all necessary guidance without redundancy.

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 7 parameters, no output schema, and no nested objects, the description is remarkably complete. It enumerates all output elements (factory choice, tile layout, code distance, qubits, time), explains the two fits always reported, specifies the infeasible return, and clarifies that the tool avoids making quantum-vs-classical conclusions. This fully compensates for the absence of an output 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?

Schema coverage is 100% with detailed descriptions for all 7 parameters, so the description doesn't need to elaborate on each field. It does add context about the core algorithm inputs (numLogicalQubits, tCount) and hardware/error-rate relationship, but these are already present in the schema. The description provides minimal additional parameter semantics beyond what's structured.

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 clearly states the tool's function: it derives the full surface-code and magic-state-distillation footprint from the Litinski lattice-surgery cost model, enumerating specific outputs (distillation factory choice, tile layout, code distance, physical qubits, wall-clock time). It distinguishes itself from siblings by focusing on fault-tolerant resource estimation from algorithm parameters, unlike compute_required_error_rate or compute_expectation.

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 specifies the input context (algorithm as numLogicalQubits/tCount and physical error rate or hardwareId) and explicitly notes that the tool only computes numbers, leaving classical comparison and decision-making to the agent. It also mentions the infeasible return for unsatisfiable error budgets, but does not explicitly reference alternative sibling tools or enumerate when to use this tool over them, though the scope is fairly clear.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior; the description complements them by disclosing the estimate's limitations: it omits reset/SPAM, mid-circuit measurement, and classical-control latency, and overstates achievable rates. This adds meaningful context beyond the bare annotation flags, though it doesn't describe response/error behavior or edge cases.

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 compact: a formula sentence, a precise interpretation sentence, and a caveat/alternative sentence. It includes no filler and front-loads the purpose before the limitations.

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 pure calculation tool with three fully documented required parameters and no side effects, the description provides enough context to select and invoke it correctly: formula, units, underlying assumptions, and known overstatement. No output schema is present, but the expected return value (QV/second) is clear from the description.

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 100%, so the baseline is 3; the description goes slightly beyond the schema by explaining how each parameter participates in the model: one native 2Q gate per QV layer and one end-of-circuit measurement. This helps an agent map t2QSeconds and tMeasurementSeconds into the stated formula, though the parameter names and schema descriptions also carry this reasonably well.

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: 'Compute the Quantum Volume Rate (QV/second)' and states the exact formula. It clearly distinguishes itself from sibling compute_* tools by naming a unique performance metric and explains what one QV-sized square circuit means.

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 clearly frames the tool as a 'first-order estimate' and explicitly warns that it 'OVERSTATES achievable rate' due to omitted real-world factors. It also points to IBM's CLOPS as a production-throughput alternative, giving a when-not-to-use hint, though it does not explicitly mention sibling compute tools.

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

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

Annotations only declare readOnly and idempotent. The description adds substantial behavioral detail beyond that: requiredLogicalErrorRatePerGate can be null only when genuinely unreachable and never 0, options above the threshold are capped with a note, and unreachableReason is reserved for genuinely unreachable options. This gives the agent a clear model of edge-case behavior.

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 generally efficient, front-loading the inverse relationship and then enumerating output semantics and edge cases. The closing 'Answers...' sentence slightly restates the purpose but reinforces user intent; overall it earns its length for a tool with this 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 complex read-only computation with no output schema, the description covers the full scope: all EC options, hardware qualification subset, per-gate logical vs physical error rates, threshold capping, notes, and null/unreachable handling. An agent has enough information to know what will be returned and how to interpret unusual results.

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%, and the schema already documents all three parameters, including constraints, units, and even the default website convention for acceptableErrorRatePercent. The description does not add much per-parameter meaning beyond tying them to the inverse calculation, so the baseline 3 is appropriate.

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 'Inverse of compute_expectation' and names the exact computation: given qubits, depth, and acceptable error, return required per-gate logical error rate and physical error rates per EC option. This clearly distinguishes it from its forward counterpart compute_expectation and other sibling tools.

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 makes the intended use case explicit by framing the tool as answering 'what hardware do I need to run this algorithm?' and by identifying the inputs and outputs. It does not explicitly state when to avoid this tool in favor of siblings like compare_hardware_scenarios, but the inverse relationship to compute_expectation provides strong contextual guidance.

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

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

Annotations declare safe read-only, idempotent operation, and the description adds important nuance about residualStdDev being biased and needing inflation for small series. This goes beyond 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?

Description is two sentences, front-loaded, and includes a key numerical caveat. Efficient despite including a formula.

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 strong schema and annotations, the description adds crucial detail about output semantics and statistical interpretation. Reasonably complete for a fit tool with no output schema, though could note edge cases like insufficient data.

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?

Input schema covers all parameters with descriptive fields; description discusses the math but doesn't add new param details beyond schema. Baseline 3 is appropriate.

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?

Clearly states it fits a log-linear trend to a historic series and names the series types. Though it could more explicitly distinguish from 'get_historic_series' (which retrieves data), it effectively communicates its function.

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?

Explicitly describes composition with other tools to answer when hardware might reach a target, providing clear usage context. Does not list exclusions or when not to use, but the guidance is strong.

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

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

Annotations already declare readOnlyHint and idempotentHint, covering safety. The description adds the fact that it 'mirrors /agent.txt served by the website' and lists content categories, which is useful context beyond annotations. No contradictions.

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 two sentences with no filler. First sentence states the action and content, second adds provenance. Perfectly front-loaded and efficient.

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 no parameters and no output schema, the description fully specifies what it returns and its source. It is complete for the agent to understand usage and expected output.

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 schema is trivially 100% covered. With 0 params, the baseline is 4. The description adds no parameter details since none exist, but it doesn't need to – it accurately describes a no-input tool.

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 clearly states the tool's function: 'Return the plain-text site brief describing scope, assumptions, the honesty clause, and the API contract.' It specifies both the action (return) and the resource (site brief), and it is distinct from siblings which are computational/list tools.

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?

While the description doesn't explicitly state 'use when you need the brief' or mention alternatives, the context makes its usage obvious. No sibling tool provides agent briefs, so the intended usage is implicit. It lacks explicit exclusions but is clear enough.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by noting the data is 'full' and 'broken down by hardware type,' and that each datapoint carries a source URL, which helps the agent understand the return structure beyond the schema.

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 two sentences, front-loaded with the main verb and resource, then followed by concrete use cases and a pairing suggestion. Every clause adds value without unnecessary fluff, making it well-structured and 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?

With one parameter, comprehensive annotations, and no output schema, the description covers all essential aspects: what the tool does, what each datapoint contains (source URL), and how it can be used in combination with fit_historic_series. The tool is simple enough that this description is fully complete.

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 schema has 100% coverage for the only parameter (seriesType), including a description of each enum value. The description repeats the meaning of 'fidelity' and 'qubit-count' but adds no new parameter-level information beyond what the schema already provides. Baseline 3 is appropriate.

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 clearly states the tool returns a full historic time series of either two-qubit gate error rates or qubit counts, broken down by hardware type. The specific verb 'Return' and explicit resource scope distinguish it from sibling tools like fit_historic_series, which fits curves rather than retrieving raw data.

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?

Explicit guidance is provided: 'Use this to extrapolate trends — "when might hardware reach X?" — or pair with fit_historic_series for a log-linear fit on one hardware type.' This clearly states when to use the tool and suggests an alternative/companion tool, fulfilling the when-to-use vs alternatives requirement.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds non-obvious context: it returns the same data as the website's table and clarifies that it provides representative entries, which helps set expectations about scope and provenance beyond the structured hints.

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?

Three compact sentences: first identifies the deliverable and its fields, second anchors it to the website table, third routes to related tools. No wasted words and critical information is front-loaded.

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?

With no parameters and no output schema, the description fully covers what the agent needs: it enumerates every returned field and the data's provenance, and it handles related queries by naming the sibling tools. Nothing crucial is missing for invoking this read-only list tool.

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, and the empty schema already conveys that. The description adds no parameter details because none exist, but it explains exactly what will be returned, which is the only relevant semantic here.

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 the tool returns a table of current SOTA quantum computers with explicit fields (id, hardware type, qubit count, error rate, connectivity, source URL), and distinguishes itself from list_quops_scores and compute_expectation by stating what those provide instead.

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?

Explicitly says to use this for the representative-entry table and directs the agent to compute_expectation for model capability prediction and list_quops_scores for measured scores, so when/where to use vs alternatives is unambiguous.

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

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses an important reliability distinction through the `provenance` field: 'published-circuit' vs 'attested-estimate.' It also instructs consumers not to present attested figures as equivalently sourced, which adds meaningful behavioral nuance beyond what annotations or schema convey.

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 front-loaded with the core action, then efficiently adds the hardware-comparison use case and the provenance caveat. Every sentence earns its place, and no content is redundant with the empty schema or annotations.

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 there are no parameters and no output schema, the description carries the full burden of defining the return payload. It covers the list contents, the resource-estimate fields, the provenance semantics, and the caveat for attested figures — enough for an agent to call the tool and interpret the result 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 tool has zero parameters, so there is nothing for the description to clarify semantically. The baseline for a zero-parameter tool is 4, and the description appropriately spends no space on params.

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 direct object: 'Return the curated list of example quantum algorithms with published resource estimates.' It states exactly what is in the returned data (qubit count, depth/gate count, source paper URL) and this clearly distinguishes it from sibling tools like list_current_quantum_computers or list_hardware_timings.

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 a clear use case: 'Useful for comparing what algorithms need vs. what hardware can deliver.' It does not explicitly name alternative tools or state when not to use it, so it stops short of a full when/when-not contract, but the intended context is evident.

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

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

Annotations already classify the tool as read-only and idempotent, and the description adds meaningful behavioral context beyond that: it discloses that the data are best-case demonstrations, that the joined device run orders of magnitude slower, and that the results include source URLs. This is important caveat information an agent could not infer from the schema or 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 four sentences with each sentence earning its place: what is returned, the key caveat, the intended use cases, and the instruction to say so when quoting a runtime. It is dense but not verbose, and the most important caveat is front-loaded.

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, so the description needs to explain return values and semantics, which it does thoroughly: gate-cycle timings in SI seconds, representativeDevice, native 2Q gate name, source URLs, and the testbed provenance caveat. The description is self-contained and leaves no important ambiguity for an agent deciding whether or how to call it.

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 is empty (0 parameters) and schema description coverage is 100%, so there is no parameter semantics gap for the description to fill. The baseline for a zero-parameter tool is high, and no further parameter-level detail is needed.

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 'Return per-platform gate-cycle timings', immediately identifying the specific resource and the exact fields returned (2Q gate time, readout time, representativeDevice, native 2Q gate name, source URLs). It also explains the join to list_current_quantum_computers, which helps distinguish this retrieval tool from the compute_* and list_* siblings.

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 states when to use the tool: 'Use for ratio analysis or as optimistic lower-bound inputs to runtime estimates and compute_quantum_volume_rate'. It also gives a clear warning that the numbers are 'BEST-CASE DEMONSTRATIONS from small testbeds' rather than measurements on the joined devices, so an agent knows not to present them as actual device performance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral nuance beyond these: it explains the fitting form (p^alpha * exp(c0 + c1*p + c2*p^2) for p <= threshold), notes that c1=c2=0 means a plain power law, and emphasizes that `provenance` and `caveats` carry source-level qualifications and that some values may be assumed or differ between sources. This warns the agent not to treat the numbers as universally firm, which is valuable. 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 a single, dense paragraph that front-loads the primary action and then logically flows from field enumeration to the fitting formula, provenance, caveats, and usage integration. Every sentence adds information — there is no filler or repetition. It is longer than the typical tool description, but given the richness of the catalog contents, it earns its length. A slightly more structured layout (e.g., bullet points) could improve scannability, but it remains efficient.

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?

With zero parameters and no output schema, the description carries the full burden of telling the agent what to expect. It exhaustively lists all returned fields, explains the mathematical fitting form and its special cases, clarifies the meaning of `provenance` and `caveats`, and instructs on how to use the returned `id` with `compute_expectation`. Nothing an agent needs to correctly invoke the tool or interpret its result 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?

The input schema has zero parameters, so there is nothing for the description to clarify about parameters. Per the rubric, 0 params yields a baseline of 4. The description does not attempt to document parameters but instead explains the output structure and the meaning of each field, which is beyond the schema's scope and thus not penalized here.

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 'Return the catalog of supported qLDPC codes' — a specific verb and resource. It enumerates the exact fields returned (id, label, family, n, k, d, circuitLevelDistance, ancilla counts, roundsPerLogicalOp, threshold, fitCoefficients, logicalErrorExponent, source URLs, provenance, caveats), leaving no ambiguity about what the tool does. It also implicitly differentiates from sibling list tools (e.g., list_current_quantum_computers) by focusing exclusively on qLDPC codes.

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 provides concrete usage guidance: 'Read it before quoting a code's logical error rate as firm' and 'Use a code's `id` as the `errorCorrectionCode` input to `compute_expectation`.' This tells the agent when to consult the catalog and how to feed its output into a sibling tool. It does not explicitly state when *not* to use this tool or name alternative catalog tools, but the context is sufficient for an agent to understand its role.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is carried structurally. The description adds provenance context — 'These are measurements, the yardstick the site's own model is checked against' — and explains why vendor/device names appear (agent-facing only), which goes beyond what annotations convey.

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 well-organized: purpose first, payload second, usage context third. Sentences about the cone constraint, arXiv reference, and agent-facing rationale each add precision or behavioral context rather than padding, though the notation requires some effort to parse.

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?

With no output schema, the description carries the full burden of explaining the return payload, and it enumerates the per-device fields (circuit size, polarization threshold, cone bound, width, QUOPS rate, architecture variants, source URL) plus the utility-scale targets. For a zero-parameter read-only list tool, 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?

The tool exposes zero parameters and the schema confirms this with 100% coverage, so there is no parameter semantics to add and the baseline 4 applies. The description instead devotes its space to the return payload, which is the more valuable information for a parameterless tool.

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 verb 'Return' plus the resource 'measured QUOPS capability scores' states exactly what the tool does, and the payload is enumerated precisely (per device, circuit size, polarization threshold, cone constraint, width, QUOPS rate, architecture, source URL, targets). The measurement-vs-model framing distinguishes it from compute_expectation and the other compute_* siblings without ambiguity.

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 contrasts measured values with model estimates by directing the agent to 'modelCapability.quopsEquivalent on the compute_expectation hardware context', effectively naming the sibling to use when a modeled value is needed. It does not provide a formal when-not-to-use list, but the measurement-vs-model distinction gives sufficient selection context.

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