QC-003 QFT phase table. phase[j]=(j*k)/n as exact rationals. n in {2,4,8}. No sqrt(n) on the wire. Floats refused.
| Name | Required | Description | Default |
|---|---|---|---|
| k | Yes | input index, 0 <= k < n, decimal, e.g. 1 | |
| n | Yes | register size: 2, 4 or 8, e.g. 4 | |
| phases | Yes | the n phases j*k/n as exact rationals, comma-separated in j order, e.g. 0/4,1/4,2/4,3/4 for n=4, k=1 |
Changes observed during successful MCP inspections.
Input schema / properties / k / descriptionAdded value: +"input index, 0 <= k < n, decimal, e.g. 1"Input schema / properties / n / descriptionAdded value: +"register size: 2, 4 or 8, e.g. 4"Input schema / properties / phases / descriptionAdded value: +"the n phases j*k/n as exact rationals, comma-separated in j order, e.g. 0/4,1/4,2/4,3/4 for n=4, k=1"Input schema / requiredPrevious value: -[]New value: +[
+ "k",
+ "n",
+ "phases"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose real input-contract behavior: n is constrained to {2,4,8}, phases must be exact rationals, floats are refused, and no sqrt(n) is accepted. That is useful validation context, but it says nothing about what the tool returns, whether it is read-only, or how failures are reported.
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?
Four short fragments, front-loaded with the artifact identity, with no wasted prose. The telegraphic style ('No sqrt(n) on the wire') is terse but each clause conveys a constraint.
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 annotations and no output schema, the description must carry the whole contract, yet it never states what the tool returns (pass/fail, which phase failed) or that it is a verification rather than a generator. For a 3-required-parameter verification tool this is an incomplete contract.
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 each property already documents its format and an example, so the baseline is 3. The description's formula phase[j]=(j*k)/n and the n-in-{2,4,8} constraint largely restate what the schema already conveys, adding little beyond it.
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 names the artifact (QFT phase table, QC-003) and gives the defining formula, which tells the agent what data is being checked, but it never says the tool verifies/validates it or what a pass means. It is distinguishable by resource (QFT phase table) from siblings like verify_shor_witness, but the action is implied rather than stated.
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?
There is no when-to-use guidance, no statement of prerequisites, and no routing to any alternative among the many verify_* siblings. The agent is left to infer that this applies only to QFT phase tables.
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.