Skip to main content
Glama
Sign In

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Extend find search

extend_find_search

Add more results to a named list on an agent.

Reuses the list's original criteria — does NOT support refinement. If the user wants to narrow the criteria, tell them to start a new list (call start_find_search with a fresh list_name).

Refuses when: no webset on file for the list, a run is already in progress, the per-list cap is already reached, or (sliq mode) the balance can't afford even one more result. When the balance covers fewer than requested, the count is clamped and the result carries a clamp_notice — surface it to the user.

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": {
      "agent_id": "<agent_id>",
      "list_name": "<list_name>"
    },
    "name": "extend_find_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idYesThe agent hosting the list.
list_nameYesThe slug the list was created with (the `list_name` column of `query_search_results`).
on_behalf_ofNoA teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.
additional_countNoHow many more results to fetch (default 20).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"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."New value: +"A teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
  2. 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."
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / list_name / description
      Previous value: -"The slug the list was created with (visible in the Output\ntab sub-pill, or via `query_search_results`'s `list_name` column)."New value: +"The slug the list was created with (the `list_name` column\nof `query_search_results`)."
  4. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "The agent hosting the list.",
+  "type": "integer"
+}
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "The task hosting the list.",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id",
-  "list_name"
-]New value: +[
+  "agent_id",
+  "list_name"
+]
  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 declare readOnlyHint=false and destructiveHint=false. The description goes well beyond: four precise refusal conditions (no webset, run in progress, per-list cap, insufficient balance), the cost model in sliq mode, and the clamping-plus-clamp_notice behavior with an instruction to surface it to the user.

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

Conciseness5/5

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

Three short paragraphs, front-loaded with the core action, then the constraint, then the failure/edge behavior. Every sentence carries information an agent needs; no filler or restatement of the title.

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?

No output schema, and the description covers the one non-obvious return detail (clamp_notice). Refusal paths and criteria inheritance are fully documented. Only minor gap is no mention of what the successfully added results look like or where to read them (query_search_results), which an agent may still have to infer.

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 baseline is 3, but the description adds real semantics for additional_count: insufficient balance causes the count to be clamped rather than failing, and a clamp_notice is returned. That is behavior the schema does not convey.

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?

Opens with a specific verb and resource: 'Add more results to a named list on an agent.' An agent can immediately distinguish this incremental-append operation from start_find_search (creates a new list) and query_search_results (reads results).

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?

Explicitly states when not to use it ('does NOT support refinement') and routes the agent to the alternative: 'tell them to start a new list (call start_find_search with a fresh list_name).' Nothing is left to inference about criteria changes.

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