Skip to main content
Glama
Sign In
Krv-Labs

topos-mcp

by Krv-Labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

topos_preference_walk

Read-onlyIdempotent

Turn a generator ranking into a preference-ordered relaxation walk. Pure and read-only (lattice math only; no files, no scoring).

Instructions

Turn a generator ranking into a preference-ordered relaxation walk. Pure and read-only (lattice math only; no files, no scoring). Call after an evaluation to pick the next verdict to aim for, or to relax the goal gracefully under a token/time budget. Returns a PreferenceWalkResult: walk (steps from target down to just above current), next_step, progress in [0, 1], aspirational_target/fallback_target, and induced_order (all 16 verdicts ranked).

Input Schema

NameRequiredDescriptionDefault
targetNoOptional aspirational-target override; defaults to IDEAL.
currentNoOptional current verdict; truncates the walk to steps strictly above it and sets `next_step`. Defaults to the full walk.
rankingYesPermutation of {simple, composable, secure, navigable}, most-preferred first.
gate_scoresNoPillar gate scores in `[0, 1]`. Enables `next_pillar`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.11.0
    • addedInput schema / properties / gate_scores
      Added value: +{
+  "additionalProperties": {
+    "format": "double",
+    "type": "number"
+  },
+  "default": {},
+  "description": "Pillar gate scores in `[0, 1]`. Enables `next_pillar`.",
+  "type": "object"
+}
    • changedInput schema / properties / ranking / description
      Previous value: -"Permutation of {simple, composable, secure}, most-preferred first."New value: +"Permutation of {simple, composable, secure, navigable}, most-preferred first."
  2. Changed3 schema fields changedv0.5.0
    • changedInput schema / $defs / GeneratorInput / enum
      Previous value: -[
-  "simple",
-  "composable",
-  "secure"
-]New value: +[
+  "simple",
+  "composable",
+  "secure",
+  "navigable"
+]
    • changedInput schema / $defs / LatticeElement / description
      Previous value: -"The 8 elements of the free Heyting algebra H(G_qual) on the three\ngenerators SIMPLE, COMPOSABLE, SECURE, mirroring `EvaluationValue` on\nthe MCP wire."New value: +"The 16 elements of the free Heyting algebra H(G_qual) on the four\ngenerators SIMPLE, COMPOSABLE, SECURE, NAVIGABLE, mirroring\n`EvaluationValue` on the MCP wire.\n\nNote for clients pinned to the pre-v0.5.0 shape: `IDEAL` now requires\nall four pillars. The verdict that used to be `IDEAL` — the top of the\nthree-generator algebra — serializes as `SIMPLE_COMPOSABLE_SECURE`.\nVariants are declared in **bitmask order**, matching\n`EvaluationValue::ALL`, so the two enums convert by position. Serde\nkeys on variant names, so this ordering is an implementation detail\nand not part of the wire contract."
    • changedInput schema / $defs / LatticeElement / enum
      Previous value: -[
-  "SLOP",
-  "SIMPLE",
-  "COMPOSABLE",
-  "SECURE",
-  "SIMPLE_COMPOSABLE",
-  "SIMPLE_SECURE",
-  "COMPOSABLE_SECURE",
-  "IDEAL"
-]New value: +[
+  "SLOP",
+  "SIMPLE",
+  "COMPOSABLE",
+  "SIMPLE_COMPOSABLE",
+  "SECURE",
+  "SIMPLE_SECURE",
+  "COMPOSABLE_SECURE",
+  "SIMPLE_COMPOSABLE_SECURE",
+  "NAVIGABLE",
+  "SIMPLE_NAVIGABLE",
+  "COMPOSABLE_NAVIGABLE",
+  "SIMPLE_COMPOSABLE_NAVIGABLE",
+  "SECURE_NAVIGABLE",
+  "SIMPLE_SECURE_NAVIGABLE",
+  "COMPOSABLE_SECURE_NAVIGABLE",
+  "IDEAL"
+]
  3. Addedv0.4.0
  4. Removedv0.4.0-rc
  5. First observedv0.3.6

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description still adds real value by scoping it as 'lattice math only; no files, no scoring' and by enumerating the return fields, which matters because no output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly three sentences, front-loaded with the core action before the guidance and return shape. Dense but each clause earns its place; no preamble or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by listing the PreferenceWalkResult fields (walk, next_step, progress, targets, induced_order), and annotations cover safety. For a pure lattice-math tool this is nearly everything an agent needs, though it could note the fixed 16-verdict domain more explicitly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds relationship semantics beyond the schema: the walk runs 'from target down to just above current' and truncates accordingly, clarifying how target and current interact rather than merely restating them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (turns a generator ranking into a preference-ordered relaxation walk) and further clarifies with 'pick the next verdict to aim for, or to relax the goal.' It is jargon-heavy ('relaxation walk', 'Heyting algebra'), but a reader can tell it apart from the assess/evaluate/refactor siblings since it computes a walk rather than a score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear sequencing context: 'Call after an evaluation to pick the next verdict to aim for, or to relax the goal gracefully under a token/time budget.' This tells the agent when to reach for it, though it names no explicit alternatives and states no when-not-to-use condition.

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

Deploy Server

Other Tools