Skip to main content
Glama

Validate Recipe Output

validate_recipe_output
Read-onlyIdempotent

Checks a host-synthesized recipe object against the expected Achiote schema, returning a valid flag and issue list so you can verify it before presenting to users.

Instructions

Validate a host-synthesized final recipe object against the expected Achiote recipe schema. Returns a validation result with valid flag and a list of issues. Use when checking a recipe before presenting it to the user. Pass recipe from the host model generate_recipe output.

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": {
      "recipe": "<recipe>"
    },
    "name": "validate_recipe_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
recipeYesHost-synthesized recipe object to validate after generate_recipe handoff

Output Schema

NameRequiredDescriptionDefault
validYes
issuesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely non-annotated context: it defines the return shape (valid flag plus issue list) and constrains the input to a host-synthesized object produced by generate_recipe, which signals the tool will reject arbitrary/unprocessed objects.

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?

Three short sentences, front-loaded with the action and resource, then usage, then input provenance. The return-value sentence is slightly redundant given an output schema exists, but it is not wasteful enough to penalize further.

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 single-parameter validator with rich annotations and a declared output schema, the description covers purpose, workflow placement, input origin, and result shape. The only gap is failure semantics – whether an invalid recipe is reported via the valid flag or as a tool error is 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?

With one parameter at 100% schema coverage, the baseline is 3, and the description earns an upgrade by specifying where the recipe must come from ('host model generate_recipe output') – provenance the schema description only hints at. It still adds no detail on what makes a recipe invalid or how nested fields are checked.

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 ('Validate') plus a specific resource ('host-synthesized final recipe object') and names the target schema ('expected Achiote recipe schema'). It also implicitly separates itself from validate_research_record by scoping to recipes, so an agent can tell the two validators apart.

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?

'Use when checking a recipe before presenting it to the user' gives a clear trigger point in the workflow, and 'Pass recipe from the host model generate_recipe output' pins the input's upstream source. It stops short of naming when-not-to-use or an alternative validator, which keeps it below a 5.

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