Skip to main content
Glama

search_mentors

Read-only

Find MentorCruise mentors who match a user's goal. Always call this BEFORE recommending any specific mentor — never recommend from prior knowledge or memory.

Inputs

  • query: 1-4 keywords (role, skill, expertise). NEVER include the words 'mentor' or 'coach'. Examples: 'python', 'product management', 'startup'. Bad: 'a python mentor for startups'.

  • skills, industries, languages, tools, companies: optional structured filters. AND across groups, OR within. Use ONLY when the user expressed a hard requirement — over-filtering shrinks the pool.

  • budget_usd_monthly: monthly USD cap for ongoing mentorship.

  • response_within_hours: max median response time.

Output

Up to 8 mentors, already ranked by composite quality. Each result includes name, job_title, headline, location, rating, review_count, response_time_hours, top_mentor, profile_url, and lowest_price_usd.

lowest_price_usd is the mentor's CHEAPEST offering — could be a one-off session ($X one-time) or a monthly subscription ($X/mo). Don't assume monthly. Phrase it as 'starting at $X' or call get_sessions_or_services to know which.

Picking which to show the user

Trust the ranking. Show 2-3, strongly preferring mentors with review_count > 0. Tie-break by more reviews → top_mentor=true. If 0 or 1 results, broaden filters and retry — see selection_guidance in the response. Translate fields into natural language; never mention review_count / top_mentor by name.

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": {
      "query": "<query>"
    },
    "name": "search_mentors"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
toolsNo
skillsNo
companiesNo
languagesNo
industriesNo
budget_usd_monthlyNo
response_within_hoursNo

Output Schema

NameRequiredDescriptionDefault
errorNoError code, e.g. 'rate_limit_exceeded'. Absent on success.
mentorsNoUp to 8 mentors, ranked by composite quality.
messageNoHuman-readable error detail.
next_stepNoSuggested follow-up tool calls.
results_countNoTotal matches found (may exceed the returned list).
recovery_hintsNoPresent only when 0 results: suggestions for broadening the search.
selection_guidanceNoHow to pick which mentors to show the user.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Beyond the given readOnly/openWorld/non-destructive annotations, it discloses result cap (up to 8), pre-existing ranking, the full result field set, the important trap that lowest_price_usd may be one-time vs monthly, and the retry-on-thin-results behavior. It does not state pagination limits or how broad a 'broaden and retry' is permitted, which keeps it from a 5.

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 critical 'call this first' rule, then organized under clear Inputs/Output/Picking headers so it is scannable rather than a wall of text. It is somewhat long and the presentation rules ('Trust the ranking', tie-break order) partially overlap, but no section is filler.

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 an 8-parameter search with a rich output payload, the description covers input conventions, ranking semantics, result interpretation, and downstream selection behavior. The output schema exists but the description still supplies the interpretive context an agent needs to use results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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

Schema coverage is 0%, so the description carries the full burden and does: query gets length and exclusion rules plus good/bad examples, filters get AND-across-groups/OR-within semantics and a caution against over-filtering, and budget_usd_monthly and response_within_hours are given units and meaning. Every one of the 8 parameters is addressed.

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 ('Find MentorCruise mentors who match a user's goal') and immediately frames the tool's scope versus the rest of the flow: it must precede any recommendation. The 'Picking which to show' section and the reference to get_sessions_or_services make the boundary against siblings concrete.

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 ('Always call this BEFORE recommending any specific mentor'), explicit when-not ('never recommend from prior knowledge or memory'), explicit constraint on over-filtering, and a defined fallback (broaden filters and retry if 0-1 results). It also names a concrete alternative for price disambiguation.

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