Skip to main content
Glama

Save a search

save_search

Use this when the user wants to keep a search to run again later. Stores the search's filters under a title, for people (the default) or for companies; the kind cannot change afterwards. To keep a search that was just run, send the filters its page answered with. Titles need not be unique, but a saved search that shares its title cannot be run by title. Free. Calling again creates a second saved search.

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": {
      "title": "<title>",
      "filters": "<filters>"
    },
    "name": "save_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoThe kind of search the filters are for. It cannot change later.people
titleYesThe saved search's title. Titles need not be unique, but a shared title cannot be run by name.
filtersYesThe search's filters, as the people or company search takes them, such as the `filters` a search page answered with.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior5/5

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

Adds real behavior beyond the annotations: the search kind is immutable after creation, repeat calls create duplicates (matching and reinforcing idempotentHint=false), duplicate titles block running by title, and the operation is free. These are consequences an agent could not derive from readOnlyHint/destructiveHint alone.

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?

Front-loaded with the when-to-use condition, then compact sentences each covering a distinct fact (type immutability, filters source, title collision, cost, duplicate creation). Some sentences duplicate schema descriptions, slightly diluting the value.

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 3-parameter create tool with a nested filters object and no output schema, the description covers trigger, immutability, duplicate behavior, and cost. It does not indicate what comes back (e.g., a saved search identifier), which would be the last useful detail given no output schema exists.

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 coverage is 100%, so all three parameters are already documented, and the description largely restates them (title uniqueness, immutable type). The one addition is guidance to pass the filters the search page answered with, which the schema already mentions, so the baseline 3 is appropriate.

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 ("keep a search to run again later", "Stores the search's filters under a title") and scopes it to people or company searches. It also separates itself from an update-style operation by noting the kind cannot change afterwards and that calling again creates a second saved search.

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

Usage Guidelines4/5

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

Opens with an explicit trigger ("Use this when the user wants to keep a search to run again later") and adds a concrete how-to for the common case of persisting a search that was just run. It does not name an alternative such as update_saved_search for modifying an existing saved search, leaving that inference to the agent.

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