Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Correct Message Classification

correct_message_classification

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceYesWhich table the message is in — 'linkedin_data' (a LinkedIn DM), 'email_data' (a sent email), or 'linkedin_queue' (a connection-request note). This is a message's `source` field from list_sent_messages or query_tagged_messages.
tag_idsYesThe corrected tag ids (from the group's tags). At most one for a single-tag comparison; an empty list clears the message to "No match".
group_idYesThe tag group the message is classified under (from list_message_tag_groups).
source_idYesThe message's row id — a message's `source_id` from query_tagged_messages.
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. Changed2 schema fields 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."
+}
    • addedInput schema / properties / source / title
      Added value: +"MessageSource"
  2. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Which table the message is in — 'linkedin_data' (a LinkedIn DM), 'email_data'\n(a sent email), or 'linkedin_queue' (a connection-request note). This is a message's\n`source` field from query_tagged_messages."New value: +"Which table the message is in — 'linkedin_data' (a LinkedIn DM), 'email_data'\n(a sent email), or 'linkedin_queue' (a connection-request note). This is a message's\n`source` field from list_sent_messages or query_tagged_messages."
  3. Changed1 schema field changed
    • changedInput schema / properties / tag_ids / description
      Previous value: -"The corrected tag ids (from the group's tags). At most one for a single-tag\ncomparison; an empty list clears the message to \"no tag\"."New value: +"The corrected tag ids (from the group's tags). At most one for a single-tag\ncomparison; an empty list clears the message to \"No match\"."
  4. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only provide the safety profile (readOnly=false, destructive=false); the description adds genuinely non-derivable behavior: the override persists across later re-tags, newly-added tags are not applied to the message, rates/message views recompute immediately, and an empty list clears to 'No match'. This is exactly the post-annotation context the dimension rewards.

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 summary is front-loaded with the core purpose and the persistence caveat is placed early where it matters. It is dense and slightly long, but nearly every clause carries a distinct fact (override, persistence, recompute, clearing).

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, but the description embeds a returns block confirming the result shape (corrected, group_id, source, source_id, tags). Combined with the behavioral disclosure, 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.

Parameters3/5

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

Schema description coverage is 100%, so all five parameters are already documented at the schema level. The description largely restates the schema's tag_ids and source guidance (at-most-one, empty clears, where to find source/source_id) rather than adding new semantics, so the baseline 3 applies.

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 (set/correct) and resource (tags on one sent message in a tag group), and explicitly scopes it to the classifier being 'wrong or skipped it'. It distinguishes itself from the bulk classifier (classify_message_tag_group) by being the per-message human override, so an agent can pick it apart from siblings without opening their 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 triggering conditions (classifier got it wrong or skipped the message), names the tools that supply the identifiers (list_sent_messages / query_tagged_messages), names the tag source (the group's tags), and states the alternative path is unnecessary ('no re-classify needed'). When-to-use is unambiguous.

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