Skip to main content
Glama

darkseal_seal_defaults

Seals a flow's default-state vector element by element at traversal start from the executing surface's witness, recording pre-ticked add-ons and pre-chosen plans and rejecting non-executing sources.

Instructions

Seal a flow's default-state vector element by element at traversal start, as captured by the executing surface's own witness module: element class, identity as presented, and default state as rendered, across checkboxes, toggles, radio/plan selectors, and continuity switches. Bundles from any non-executing source are rejected on provenance. The check is free. Darkseal seals the state the flow started in — every pre-ticked add-on, pre-chosen plan, and continuity toggle, element by element — at the moment your agent entered it. If a charge began as a default you never chose, the sealed record names the element it began as, and anyone can recompute the verdict from the record itself.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "flow_id": "<flow_id>",
      "elements": "<elements>",
      "surface_attestation": "<surface_attestation>",
      "surface_id": "<surface_id>",
      "source": "<source>"
    },
    "name": "darkseal_seal_defaults"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYes
flow_idYes
elementsYes
flow_kindNo
surface_idYes
grammar_coverageNo
surface_attestationYes
traversal_timestampNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose useful behavior — provenance rejection for non-executing sources, that the operation is free, and that the sealed record is independently recomputable. It does not say whether the seal persists state, whether repeat calls are idempotent, what permissions the surface_attestation requires, or what a rejection looks like, which is a notable gap for a mutation-flavored tool.

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

Conciseness2/5

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

The text is padded and repetitive: 'element by element' appears twice, and 'at traversal start' is restated as 'at the moment your agent entered it', with a second enumeration of toggles and pre-chosen plans. The provenance rejection and the free-of-charge note are buried mid-paragraph rather than front-loaded, so the agent must parse marketing phrasing to extract the operational facts.

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

Completeness2/5

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

For an eight-parameter, five-required tool with no annotations, no output schema, and zero schema coverage, the description is not complete enough: the formats of surface_attestation, source, and grammar_coverage, and the role of traversal_timestamp and flow_kind are all left unexplained. It conveys the concept and provenance rule but not enough to construct a valid call without trial and error.

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

Parameters3/5

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. It does explain the nested elements fields (class, identity as presented, default_state as rendered) and implicitly ties 'executing surface's own witness module' to surface_attestation/surface_id and 'source' to provenance. It says nothing about flow_id, flow_kind, grammar_coverage, or traversal_timestamp, so half of the eight params remain undocumented everywhere.

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

Purpose3/5

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

The description names a specific action ('Seal a flow's default-state vector') and enumerates the element classes it covers (checkboxes, toggles, radio/plan selectors, continuity switches), so the general purpose is inferable. However, it leans on undefined jargon ('executing surface's own witness module', 'traversal start') and never plainly states what a caller gets back or how it differs from siblings like darkseal_check or darkseal_recompute, which it only obliquely gestures at.

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 or when-not-to-use guidance and no named alternative among the five siblings. 'The check is free' implies a cost trade-off and 'bundles from any non-executing source are rejected on provenance' is an input constraint, not routing guidance, so the agent must guess when to pick this tool over darkseal_check.

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