Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal).
Returns the corrected state, corrective delta vector Delta S = S* - S, and boundary distance margins.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | ||
| lattice_id | No | ||
| lattice_data | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of explaining behavior. It does disclose the return values ('corrected state', 'delta vector', 'boundary distance margins'), but does not state whether the operation has side effects, requires prior context such as a compiled lattice, or how it handles invalid or missing inputs.
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 and front-loaded: the core action and mathematical context appear first, followed by the return values. Both sentences add meaningful information with no filler or repetition.
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 the mathematical complexity, the lack of annotations, and zero schema-level parameter documentation, the description is not sufficient for an agent to reliably decide what to pass. It does not explain how lattice_id and lattice_data affect the projection, what S0 and Goal map to, or what 'boundary distance margins' represent operationally.
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 0%, so the description must compensate for the three undocumented parameters. It clarifies that 'state' is the candidate state being projected, but never explains how lattice_id or lattice_data relate to S0, Goal, or the manifold construction, leaving key inputs ambiguous.
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 identifies the action ('Project') and the resource ('a candidate state or plan step onto the Singular Transition Manifold'), with a precise mathematical definition. It does not explicitly contrast with sibling tools like cognitive.verify_lattice_transition or cognitive.synthesize_singular_path, but the projection-focused purpose is distinct enough.
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 phrase 'Project a candidate state or plan step...' implies when to use the tool: when a state or plan step needs to be corrected onto the manifold. However, it gives no explicit when-not-to-use guidance, alternatives, or preconditions such as requiring lattice_id or lattice_data.
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.