Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Retry Blocked Enactment

retry_blocked_enactment

A retry with the cause still in place fails and re-blocks identically — fix the cause in the same call: pass email for an email-shaped block (email_not_found, a missing address) and/or linkedin_url for a wrong or missing LinkedIn identifier (missing_identifier, a failed resolution). Both fix the EXISTING prospect's person — never re-add the person via track_prospects with the new contact info, which creates a duplicate prospect. A cr_already_sent block has no fix here: Sliq's records show it already sent this person a connection request. Tell the user; if they have since re-invited by hand, register_manual_linkedin_invites picks the campaign up from that invite; otherwise drop the prospect with update_prospect(stage='skipped'). A name_mismatch block means the LinkedIn profile belongs to someone other than the person they were added as (data.supplied_name): retrying continues the campaign with that profile — do it only when it's the same person under another name; otherwise skip the prospect and track the intended person (a linkedin_url fix is refused on this block). Dict confirming the prospect, the node they rest on, the cleared reason, and any contact fixes applied (email / linkedin_url). An email fix lands on the person's profile, the prospect's only address.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailNoAn address to stamp on the prospect before retrying (optional) — the same write as update_prospect's `email`; refused if another person in the workspace already carries it.
agent_idYesID of the agent whose flow the prospect is on.
prospect_idYesThe prospect's `id` — the outreach_prospects primary key, as returned on every query_prospects row.
linkedin_urlNoA corrected LinkedIn profile URL or slug (optional). Applied as an unverified claim the retried send verifies through the profile resolver, so a wrong-person pairing is held for adjudication like any other. On a previously-verified profile (a dead or reassigned URL) the old verification is cleared and the corrected identity re-verifies fresh; refused only when a teammate's prospect verified the same person — remove this prospect and track the correct profile instead.
on_behalf_ofNoAn agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / email / description
      Previous value: -"An address to stamp on the prospect before retrying (optional) — the\nsame write as update_prospect's `email`; refused if another prospect in\nthe account already owns it."New value: +"An address to stamp on the prospect before retrying (optional) — the\nsame write as update_prospect's `email`; refused if another person in the\nworkspace already carries it."
  3. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "ID of the agent whose flow the prospect is on.",
+  "type": "integer"
+}
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "ID of the task whose flow the prospect is on.",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id",
-  "prospect_id"
-]New value: +[
+  "agent_id",
+  "prospect_id"
+]
  4. Changed1 schema field changed
    • changedInput schema / properties / linkedin_url / description
      Previous value: -"A corrected LinkedIn profile URL or slug (optional). Applied as\nan unverified claim the retried send verifies through the profile\nresolver, so a wrong-person pairing is held for adjudication like any\nother. Refused once a live lookup verified the current profile — a\ndifferent URL then means a different person: remove them from the\ncampaign and track the correct profile instead."New value: +"A corrected LinkedIn profile URL or slug (optional). Applied as\nan unverified claim the retried send verifies through the profile\nresolver, so a wrong-person pairing is held for adjudication like any\nother. On a previously-verified profile (a dead or reassigned URL) the\nold verification is cleared and the corrected identity re-verifies\nfresh; refused only when a teammate's prospect verified the same\nperson — remove this prospect and track the correct profile instead."
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds substantial context beyond that: it mutates person contact data, retry is asynchronous (~15 min, longer when queued), a retry with the cause still present re-blocks identically, and certain fixes are refused (linkedin_url on name_mismatch).

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?

It is long, but front-loaded with a <summary> and each sentence carries a distinct constraint (timing, per-block fixes, refusal conditions). Dense rather than padded, though the volume is at the edge of what an agent needs in one read.

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

Completeness5/5

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

No output schema exists, and the description supplies a <returns> block describing the confirmation payload. Combined with the per-block guidance and async timing, an agent has everything needed to call it correctly.

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 real meaning: it maps `email` to email-shaped blocks and `linkedin_url` to identifier blocks, and warns the fix applies to the EXISTING prospect rather than re-adding via track_prospects. This goes beyond the schema's per-field text.

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

Purpose5/5

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

States a specific verb and resource ('clear a prospect's blocked flow step so it retries') plus the side effect of fixing contact info in the same call. It explicitly names related siblings it is not (report_enactment_blocked, query_prospects, track_prospects), so an agent can distinguish it without opening schemas.

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?

Gives explicit when-to-use ('blocked prospect is excluded from every enactment selection until unblocked'), when-not ('cr_already_sent has no fix here'), and alternatives per case (register_manual_linkedin_invites, update_prospect(stage='skipped'), track_prospects). The block-reason taxonomy maps conditions to the right action.

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

All Sliq toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources