Skip to main content
Glama

Search entries

search
Read-onlyIdempotent

Search Daawid's open registry of people, businesses and organizations by what the user needs, such as 'a dentist in Nairobi' or 'a CRM for a small team'. Each result says who it is, where, and whether it takes on work; get_entry shows one to the user, get_entry_sections reads parts of one.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly people, or only organizations.
nearNoThe place the user asks about, which they named. Entries there or serving it come first, then the nearest. Never coordinates or a street address.
limitNo
queryYesWhat the user is looking for, in a few words: "carpenter", "fontanero urgente", "CRM". The place goes in `near`, and what they want to achieve in `outcome`.
cursorNonextCursor of the previous page.
openAtNoOnly entries open at this moment, by their stated hours: "2026-11-06T18:30:00+01:00". Only when the user asks what is open.
outcomeNoWhat the user wants to achieve with it, in a few of their words: "keep track of leads in a small team", "fix a leaking tap today". It helps the best fits come up and leaves nobody out. No names or personal details.
categoryNoOnly this category ("trades.carpentry") or sector ("trades").
languageNoThe language the user writes in: "ja". Summaries come in it, when the entry has it.
radiusKmNoOnly within this many km of `near`. Only when the user names a distance; there is no default.
verifiedOnlyNoOnly entries whose owner proved control of their website.
acceptingWorkNoOnly entries that state they take on new work now.

Output Schema

NameRequiredDescriptionDefault
hitsYes
placeNo
nextCursorNo
rankingPolicyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds that each result reports identity, location and whether the entry takes on work, which is useful behavioral context, but it does not discuss pagination, result volume, or ranking behavior beyond the schema's own notes.

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?

Two sentences, front-loaded with the purpose and ending with the sibling routing. Every clause carries information; nothing is repeated from the schema or annotations.

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 12-parameter search tool, the description covers purpose, query phrasing, and the follow-up path, while the rich schema and the presence of an output schema handle parameter and return-value detail. It is nearly complete, with only ranking and pagination behavior left implicit.

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 92%, so the baseline is 3, and the description earns above that by disambiguating parameters: it tells the agent to put the place in `near` and the goal in `outcome` rather than in `query`. That routing rule is meaning the schema alone does not make obvious.

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 ("Search Daawid's open registry of people, businesses and organizations") and grounds it with two concrete query examples. It also names the sibling tools get_entry and get_entry_sections, so an agent can distinguish this discovery tool from the retrieval tools 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 Guidelines4/5

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

The closing sentence routes the agent: search here, then use get_entry to show one entry or get_entry_sections to read parts of one. That is clear context for the follow-up step, but there is no explicit statement of when not to use this tool or of prerequisites.

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