Skip to main content
Glama

Start a search

createRoleSearch

Start a Search for a role (jobId from readJob), or an exploring Search from a prompt alone, and start its first run. It searches the Clera pool, your team's network and, when turned on, outside Clera; people appear on the Search as they are scored.

Needs jobId, prompt, or both. A role alone uses the role's requirements as criteria. A role with a prompt keeps those and adds up to 2 criteria from the prompt. A prompt alone is drafted into criteria by Clera. Tell the user what will be searched and get a yes before calling: each run uses search credits. Then read the result with getRoleSearch.

Clera privately records this tool's inputs and results for usage tracking and support.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "createRoleSearch"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdNoThe role to search for.
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
promptNoWho to look for, in the user's words.

Output Schema

NameRequiredDescriptionDefault
runIdYes
searchYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly=false, idempotent=false, openWorld=true, but the description adds material context beyond them: each invocation consumes search credits, non-idempotency is grounded ('start its first run' creates a new object), external sourcing depends on a setting, people are scored asynchronously, and inputs/results are privately recorded. That async/scoring behavior is not inferable from annotations.

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 purpose, then input combinations, then the confirmation and credit warnings, then the follow-up pointer — a sensible ordering. It is dense and three paragraphs long; the closing data-recording sentence is compliance boilerplate rather than invocation guidance, though it is arguably required disclosure.

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?

For a write tool with optional parameters, an output schema, and open-world behavior, the description supplies everything an agent needs to call it correctly: which inputs are valid in which combination, the user-consent gate before spending credits, the async nature of results, and where to retrieve them. No important gap remains.

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 earns credit for explaining interaction semantics the schema cannot: jobId alone reuses the role's requirements as criteria, jobId plus prompt adds up to 2 criteria from the prompt, and prompt alone is drafted into criteria. orgId is left to its schema description, which is adequate.

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 ('Start a Search') and immediately enumerates the two creation modes: role-based via jobId from readJob, or prompt-only. It also discloses the search scope (Clera pool, team network, outside Clera when enabled), which lets an agent distinguish this from sibling tools like getRoleSearch or runRoleSearch without opening a 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?

Explicitly covers the when-to-use conditions ('Needs jobId, prompt, or both'), the three input combinations and their effects, a hard prerequisite ('Tell the user what will be searched and get a yes before calling'), the cost rationale (search credits), and the correct follow-up tool (getRoleSearch). This is unusually complete routing guidance.

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