Skip to main content
Glama

Ni Biashara Shelves — Africa FX, freight & compliance checks (x402)

Recipe search — dishes as structured data

search_recipes
Read-only

Recipe search — dishes as structured data. Search the Ni Biashara recipes shelf: dishes as thick structured records (ingredients with quantities and units, timed steps, substitutions, dietary tags, and sourcing notes for diaspora buyers). Filter by text, cuisine, region, dietary tag or total-time budget. v1 launches with the fully worked Kenyan beef pilau record and grows through the daily depth pass. $0.25 USDC on Base. Returns the x402 URL to GET (402 → PAYMENT-SIGNATURE → delivery). Free to call this tool; payment happens on the URL.

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_recipes"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNofree text over title, cuisine, region, tags and ingredient names (optional)
limitNomax records to return (optional, default 25, max 60)
offsetNorecords to skip (optional, default 0)
regionNoregion text, e.g. Kenyan Coast (optional)
cuisineNoexact cuisine, e.g. Kenyan (optional)
dietaryNodietary tag on the record, e.g. gluten-free (optional)
max_minutesNoonly dishes whose total time is at most this many minutes (optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior5/5

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

Annotations only say readOnly/openWorld/non-destructive; the description adds behavior the schema and annotations cannot express: the $0.25 USDC on Base price, that the tool itself is free, and the exact handshake 'Returns the x402 URL to GET (402 → PAYMENT-SIGNATURE → delivery).' It also discloses catalogue maturity ('v1 launches with the fully worked Kenyan beef pilau record and grows through the daily depth pass'), warning the agent that results may be sparse. None of this contradicts readOnlyHint=true — the tool only reads; payment occurs off-tool on the returned URL.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The middle of the description is dense and useful, and the payment mechanics are front-loaded near the end where they belong. But the opening sentence 'Recipe search — dishes as structured data' is a verbatim restatement of the title, and the long parenthetical about record contents packs several ideas into one clause. Trimming the title echo would cost nothing.

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?

There is no output schema, so the description must carry the return contract — and it does, stating that the tool returns an x402 URL to GET and describing the record payload qualitatively (quantities, timed steps, substitutions, sourcing notes). Combined with the disclosed price and the v1 scope caveat, an agent has enough to call this correctly and know what comes back. Only the concrete response envelope (URL field shape, list vs. object) is left unstated.

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 all seven parameters are already self-documenting, and the baseline is 3. The description's filter list mirrors the schema rather than extending it — it adds no syntax, matching behavior, or interaction rules (e.g. how q combines with cuisine). The only genuine addition is the implicit warning that narrow filters may match only the single pilau record.

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?

Specific verb+resource ('Search the Ni Biashara recipes shelf') with scope qualifiers: dishes as structured records with ingredients, steps, substitutions, tags and sourcing notes. It enumerates the filter dimensions, so an agent knows exactly what kind of query this answers. It stops short of naming a sibling (e.g. get_recipe for a single known dish), so it earns a 4 rather than 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 Guidelines3/5

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

It gives real usage context — 'filter by text, cuisine, region, dietary tag or total-time budget' — and a critical cost cue: 'Free to call this tool; payment happens on the URL.' That resolves the main decision an agent faces (search is free, retrieval/payment is not). However, it never states when to prefer this over get_recipe or the collection dossier, and no exclusion or fallback is given, so guidance is implied rather than explicit.

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