Skip to main content
Glama

omniseek_curator_act

Manage source-curation lifecycle actions such as submit, probe, decide, admit, retire, or roll back, while applying safety gates before changing curated sources.

Instructions

Use WHEN acting on the source-curation protocol: WRITE a source-lifecycle action (submit / probe / decide / admit / retire ...); every safety gate lives in the impl, unchanged. Pick the action with verb; the other arguments are that verb's: submit (name, urls, mode, domain, family; optional kind, regions, rationale, draft): add a candidate; mode is STRUCTURE / UNWALL / TRANSCRIBE / RECALL / MONITOR. probe (candidate_id): gather the evidence; returns the packet. wall_probe (candidate_id): re-probe by rendering it in the isolated browser (a parked_p2 candidate, or one you judge a client-rendered shell). decide (candidate_id, decision, reasons; baseline_ref to admit): admit / watch / reject. Refused: an admit with a hard red line, incomplete evidence, an empty baseline_ref or no packet. apply_live (candidate_id): reversible live admit, rss-safe families only (others use stage_commit). rollback_live (name, family): undo apply_live. stage_commit (candidate_id): prepare the git commit text for a non-auto family; the operator commits. retire_live (name; confirm): needs a PRUNE verdict; confirm=False previews, True writes a reversible override. rollback_retire (name): undo retire_live. source_verdict (name, verdict, rationale; prune_class, coverage_impact): KEEP / WATCH / PRUNE an existing source. Refused: a PRUNE its safety flags forbid.

Tool name: omniseek_curator_act (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_curator_act".

An unknown verb returns an error listing the valid values. Protocol: the /curator skill. More: omniseek docs/TOOLS.md, omniseek_curator_act.

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": {
      "verb": "<verb>"
    },
    "name": "omniseek_curator_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
modeNo
nameNo
urlsNo
verbYes
draftNo
domainNo
familyNo
confirmNo
reasonsNo
regionsNo
verdictNo
decisionNo
rationaleNo
prune_classNo
baseline_refNo
candidate_idNo
coverage_impactNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations supply only readOnlyHint=false, so the description must carry behavior, and it does: safety gates 'live in the impl, unchanged', which verbs are reversible (apply_live rollback_live, retire_live rollback_retire), that stage_commit only prepares text and 'the operator commits', and that confirm=False previews while True writes. It also discloses error behavior for unknown verbs. This is materially more than a mutation flag.

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?

The WHEN clause is front-loaded and the verb list is a scannable one-line-per-verb structure that suits an 11-verb dispatcher. Nearly every line carries operative information. The trailing meta-block about MCP prefixes and ToolSearch fallback is environment boilerplate that does not help select or invoke the tool, and 'More: docs/TOOLS.md' adds little.

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?

For a dispatcher bundling 11 verbs across 18 undocumented parameters with no output schema, coverage is strong: argument sets, refusal rules, reversibility, and the one stated return value (probe 'returns the packet') are all present. What is missing is any definition of the 'family' taxonomy and the semantics of coverage_impact/baseline_ref objects, which an agent must still infer or look up in the referenced docs.

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 0% and 18 parameters exist, so the description must compensate, and it largely does: it maps each parameter to its owning verb and enumerates vocabularies the schema leaves as bare strings (mode = STRUCTURE/UNWALL/TRANSCRIBE/RECALL/MONITOR, decision = admit/watch/reject, verdict = KEEP/WATCH/PRUNE). Residual gaps remain for prune_class and coverage_impact, which are named but never explained, and for the 'family' value space ('rss-safe families', 'non-auto family') which is referenced without enumeration.

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?

The opening clause states a specific verb and resource: 'WRITE a source-lifecycle action' on the source-curation protocol, with the concrete verb set (submit/probe/decide/admit/retire...) enumerated. It is clearly the mutation counterpart to the sibling omniseek_curator_view. The only friction is that 'source-curation protocol' is domain jargon that presumes the /curator skill, so a cold agent gets a precise shape but not a plain-language statement of what curation means here.

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

Usage Guidelines5/5

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

It gives an explicit trigger ('Use WHEN acting on the source-curation protocol'), a selection rule for the sub-action ('Pick the action with ``verb``'), and per-verb when-to-use conditions. It also names alternatives: apply_live is limited to rss-safe families while 'others use stage_commit', and wall_probe is for 'a parked_p2 candidate, or one you judge a client-rendered shell'. Refusal conditions (admit with a hard red line, empty baseline_ref, no packet; PRUNE forbidden by safety flags) tell the agent when not to proceed.

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