Skip to main content
Glama

Verify Reconstruction

verify_reconstruction
Idempotent

Verifies typed behavioral and structural claims against canonical Evidence, confirming comparable authority per claim and flagging changed claims failed and missing or unresolved evidence unknown.

Instructions

Verify a finite typed behavioral and structural specification against a canonical Evidence bundle. Pass means every declared claim has complete comparable authority—not global source equivalence; changed claims fail and missing, limited, or unresolved evidence stays unknown.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "specification": {
        "name": "Terminal compatibility",
        "claims": [
          {
            "kind": "behavioral",
            "title": "Terminal output remains equivalent",
            "claim_id": "terminal-output",
            "dimension": "terminal",
            "comparison_evidence_id": "ev_5f5ed94fee174c3957930ff6e992c9618fa1757001cf04d824846ab1124636a5"
          }
        ]
      }
    },
    "name": "verify_reconstruction"
  }
}

Input Schema

NameRequiredDescriptionDefault
specificationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare read-only=false, destructive=false, idempotent=true, openWorld=false, so the safety profile is covered. The description adds real value by disclosing a tri-state outcome model: pass when every claim has complete comparable authority, fail on changed claims, and 'unknown' for missing/limited/unresolved evidence. It still omits what a partially-failing result looks like per claim and any error behavior.

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?

Two dense sentences, front-loaded with the core action before the outcome semantics. Nothing is redundant, though the em-dash clause is syntactically heavy and slightly obscures the key rule.

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

Completeness3/5

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

With a complex nested input schema and no output schema, the description should explain outcomes and inputs more fully. It does describe the pass/fail/unknown result semantics, which is the essential returned information, but leaves the claim taxonomy and evidence-ID requirements unexplained.

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?

Only one top-level parameter with a deeply nested schema whose description coverage is near zero, so the description must carry weight. It does clarify that the specification is a set of 'declared claims' each needing comparable authority, which explains why comparison_evidence_id exists and what makes a claim valid. It does not explain claim kinds, dimension enums, or the ev_ identifier format.

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 and object: verify a typed behavioral/structural specification against a canonical Evidence bundle. It is clearly distinct from binary-analysis siblings, though the heavy jargon ('complete comparable authority', 'finite typed') makes the exact contract hard to parse on first read. It does not name or contrast any sibling.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance, no prerequisites, and no routing to alternatives such as verify_rust_parity or verify_managed_native_boundaries. The only guidance is outcome semantics (what Pass means), not selection criteria.

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