QC-016 Teleport reconstruction. bob = alice XOR corrections on 2 bits. Floats refused.
| Name | Required | Description | Default |
|---|---|---|---|
| bob | Yes | Bob's reconstructed two bits, must equal alice XOR corrections, e.g. 01 | |
| alice | Yes | Alice's two measurement bits, e.g. 10 | |
| corrections | Yes | the two Pauli-correction bits Bob applies, e.g. 11 |
Changes observed during successful MCP inspections.
Input schema / properties / alice / descriptionAdded value: +"Alice's two measurement bits, e.g. 10"Input schema / properties / bob / descriptionAdded value: +"Bob's reconstructed two bits, must equal alice XOR corrections, e.g. 01"Input schema / properties / corrections / descriptionAdded value: +"the two Pauli-correction bits Bob applies, e.g. 11"Input schema / requiredPrevious value: -[]New value: +[
+ "alice",
+ "bob",
+ "corrections"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It usefully discloses an input-validation trait ('Floats refused') and defines the relational invariant being verified, but says nothing about return values, pass/fail signaling, or error behavior on mismatch. Partial disclosure for a tool with no annotation cover.
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 tight fragments, front-loaded with the operation identity and the defining constraint. Nothing is padded. The only cost is the opaque 'QC-016' identifier, which consumes a slot without explaining itself.
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 verification constraint is fully specified, which is the core need for a 3-param check tool. However, with no output schema the description never indicates what a verification returns (boolean, error, or confirmation string), leaving the agent to guess the outcome 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 coverage is 100% with per-parameter examples, so the baseline is 3. The description adds genuine cross-parameter semantics not present in the schema: the constraint that bob, alice, and corrections are related by XOR over exactly 2 bits. That is real added meaning beyond the individual field docs.
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 specific resource (quantum teleportation reconstruction) and defines the exact check performed: 'bob = alice XOR corrections on 2 bits.' An agent can tell this apart from other verify_* siblings by topic, though no sibling is named explicitly. The purpose is concrete, not a tautology.
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?
No when-to-use or when-not-to-use guidance is given, and no alternative among the ~20 verify_* siblings is referenced. Usage must be inferred entirely from the name and the XOR constraint. This is a real gap in a dense verification family.
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.