Skip to main content
Glama

El Trabajito directory

search_businesses

Read-onlyIdempotent

Search the directory of independent workers and small businesses in Costa Rica (gardeners, painters, plumbers, electricians, cleaners, bakers, mechanics and more). Results are ranked by customer rating, then by number of reviews. Pass a free-text query ("panadera", "plumber"), optionally a category slug from list_categories, a place name, a minimum rating or kind. Always include the profile url when you recommend someone.

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": "search_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoRestrict to individual workers (person) or companies (business). Leave out for both.
limitNoUp to 10 (default 5).
placeNoTown or area, for example "Santa Ana" or "Heredia".
queryNoWhat the person needs, in Spanish or English.
categoryNoCategory slug from list_categories, for example "painting".
languageNoLanguage of the names and links in the answer (default es).
minRatingNoOnly return profiles whose average rating is at least this many stars (0 to 5). Unrated profiles are excluded when it is above 0. Default 0.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / kind / description
      Added value: +"Restrict to individual workers (person) or companies (business). Leave out for both."
    • addedInput schema / properties / minRating / description
      Added value: +"Only return profiles whose average rating is at least this many stars (0 to 5). Unrated profiles are excluded when it is above 0. Default 0."
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: result ordering by rating then review count, and the instruction to surface profile URLs in recommendations. It does not describe result volume or what happens when no match is found, which limits it to a 3.

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 sentences, front-loaded with the scope and entity types, then how to call it, then the output expectation. The parenthetical examples are short and functional; no sentence is redundant.

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 7-parameter, all-optional tool with no output schema and full annotation coverage, the description supplies enough to call it correctly: query style, ranking, cross-tool slug source, and the URL-in-response expectation. What an actual result record contains beyond the profile URL remains unspecified.

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 description coverage is 100%, so every parameter is already documented, which sets the baseline at 3. The description adds modest value by pairing parameters ('query' in Spanish or English, category slug sourced from list_categories) but introduces no semantics beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Uses a specific verb and resource: 'Search the directory of independent workers and small businesses in Costa Rica', and enumerates the entity types covered (gardeners, painters, plumbers...). It does not explicitly contrast itself with siblings like top_rated or get_business, so an agent must infer that boundary from the ranking note, which keeps it just short of a 5.

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?

Gives clear invocation guidance: pass a free-text query, optionally add a category slug from list_categories, a place, minRating, or kind, with concrete example queries. It links to the sibling list_categories for slug discovery but never states when NOT to use this tool versus top_rated or get_business.

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