Skip to main content
Glama

Run a saved search

run_saved_search
Destructive

Use this when the user wants the people a saved people search finds now. The stored filters are the search: the arguments only page it (limit, cursor) or narrow it to one person (linkedinUrl). Stored filters the search no longer takes are left out and reported. A saved company search is refused here; it runs as a company search given the saved search's id. Costs $0.001 per person returned, charged to the organization's balance; an empty page is free. Calling again with the same arguments charges again.

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": {
      "savedSearchId": "<savedSearchId>"
    },
    "name": "run_saved_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPeople per page. The page's most possible cost, `limit` times $0.001, is held from your balance first.
cursorNoThe `pagination.nextCursor` of the page before. Send it with the same search, as the `filters` the first page answered with.
detailNoHow much of each row to return. `short` (the default) leaves out the long fields; `full` returns every field, so ask for few rows with it.short
linkedinUrlNoNarrow the saved search to one person, by LinkedIn profile URL.
savedSearchIdYesThe saved search's id.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: per-person pricing ($0.001 per person returned, charged to the org balance), free empty pages, repeat-call charging (consistent with idempotentHint=false), and the side effect that stored filters no longer accepted are dropped and reported. The one gap is that destructiveHint=true is never explained — nothing in the description says what is destroyed or what lingering effect justifies that flag.

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?

Four short sentences, front-loaded with the use condition, then scope constraints, then the sibling refusal, then cost. No filler and no repetition of schema-documented mechanics.

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 paid, paginated, non-idempotent search with no output schema, it covers cost, pagination chaining, narrowing, and stale-filter handling well. It stops short of describing the shape of a returned person row or the 'reported' dropped-filter surface, which leaves a small gap given there is no output schema.

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?

With 100% schema coverage the baseline is 3, and the description goes further by clarifying that the arguments cannot override the stored filters — they only page (limit, cursor) or narrow to one person (linkedinUrl). Minor omission: `detail` is not mentioned in that enumeration, so the agent might read the list as exhaustive.

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+resource ('Run a saved search' returning 'the people a saved people search finds now') and separates it from sibling families by refusing company searches ('A saved company search is refused here'), routing the agent to the company-search equivalent. An agent can tell this apart from get_saved_search, list_saved_searches, or search_people without opening another schema.

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?

Explicit when-to-use trigger ('when the user wants the people a saved people search finds now'), explicit when-not (saved company searches are refused; run them as a company search with the saved search's id), and an explicit caution about re-running ('Calling again with the same arguments charges again'). The constraints on what arguments can do are also spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources