Xenition

Search public listings

discover_search

Read-only

Look up real, current information from open public sources: jobs, hospitals, clinics, pharmacies, banks, schools, universities, companies, government offices. Reads the sources live at the moment of asking rather than from a stored copy, so it is current. Place types (hospitals, schools, banks, pharmacies, clinics, government offices) REQUIRE near. Always tell the user which sources answered and when. Each result may carry phone, website, address, lat/lng and a detail map (salary, cuisine, opening hours). QUOTE THEM — a phone number or an apply link that came back and was not shown is the answer the user asked for, thrown away. Do NOT web-search for a detail that is already in the result. Where a field is genuinely absent, say so for that entry rather than searching 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": {
      "type": "<type>"
    },
    "name": "discover_search"
  }
}

Input Schema

Name	Required	Description
`lat`	No	latitude of the user, when the conversation states it — use with lng instead of guessing a place name for 'near me'
`lng`	No	longitude of the user, when the conversation states it
`near`	No	a place — a city, an address, a neighbourhood
`type`	Yes	which catalogue: jobs, hospitals, clinics, pharmacies, banks, schools, universities, companies, gov_offices, events, flights
`query`	No	what to look for — a job title, a company name, a university
`radiusKm`	No	how far to look, in kilometres (default 5)

Output Schema

Name	Required	Description	Default
`count`	Yes
`empty`	No
`items`	Yes
`title`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 3, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, openWorld and destructive=false, so the safety profile is covered. The description adds genuinely new behavior: sources are read live at query time (which explains and reinforces idempotentHint=false), the returned field set (`phone`, `website`, `lat`/`lng`, `detail`), and a hard input requirement that place types need `near`.

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?

Purpose and the `near` requirement are front-loaded, and most sentences carry operational instructions that affect call correctness. It is on the long side, with the last two sentences (don't re-search, state absent fields) restating the same 'use what you got' idea twice, and the all-caps emphasis is heavier than needed.

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 an open-world search tool with an output schema present, the description covers the important gaps: live-vs-cached semantics, required location for place types, and how to report results. It omits result limits/pagination behavior and any relationship to the similarly-named `discover_sources` sibling.

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 schema already documents each parameter and the baseline is 3. The description adds real cross-parameter semantics the schema cannot express — that place-type values require `near`, and that lat/lng should be used instead of guessing a place name for 'near me'. The `type` value list largely duplicates the schema description.

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?

States a specific verb and resource — 'look up real, current information from open public sources' — plus an explicit enumeration of the catalogues it covers (jobs, hospitals, banks, schools, etc.), which is far beyond a restatement of the name. It does not, however, differentiate itself from the sibling `discover_sources`, whose name is close enough that an agent could confuse the two.

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 concrete usage constraints: place types REQUIRE `near`, results must be attributed with sources and timing, and details already returned should not be re-searched. It lacks any explicit routing to an alternative tool (e.g. `discover_sources` or `find_tools`), so the agent gets context but not exclusions.

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

All Xenition tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.