Mostly Right

Suggest where a run's table could use a rule or a model

suggest_enrichments

Read-onlyIdempotent

Reads the run's columns, then a bounded sample of its text columns (up to max_rows rows, default 50, each value cut to its first few thousand characters; metered like query_run, the column read is not charged) and names, column by column, a deterministic derivation (cast text to its type, parse machine-coded text, map a code list to labels, a normalized key to join or dedupe on) or a model call (classify, extract, match) that would improve the table, each with model_status for the model it needs and the binding to use. It spends no model call and changes nothing. Example: {"run_id": "…"}. Returns {run_id, analyzer, sampled_rows, opportunities: [{column, task, method, why, next_step, stats, model_status?, binding?}], omitted, models, offer}. Treat each entry as a lead: confirm it against the rows before you offer it, deterministic ones first. Add a model source only when the person agrees or the brief asked for that judgement; a model_status other than available is offered as coming. The sampled rows are not returned. A timeout or a usage limit answers as query_run's would.

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": {
      "run_id": "<run_id>"
    },
    "name": "suggest_enrichments"
  }
}

Input Schema

Name	Required	Description	Default
`run_id`	Yes
`max_rows`	No
`wait_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 23, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses sampling bounds (up to max_rows, default 50), value truncation, charging semantics (column read not charged, metered like query_run), that sampled rows are not returned, and that timeouts/usage limits behave as query_run's. This is rich behavioral context beyond structured fields.

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?

The purpose and sampling behavior are front-loaded, and much of the length is justified by output-shape and usage detail. It is dense and could trim some of the output-field enumeration, but each sentence largely earns its place.

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?

With no output schema, the description does the work of describing the return shape (run_id, analyzer, opportunities with fields, omitted, models, offer) and caveats, which is strong. The unexplained wait_seconds parameter is the main remaining gap.

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 coverage is 0%, so the description carries the burden. It explains max_rows semantics (up to max_rows rows, default 50) and shows run_id in an example, but wait_seconds is never mentioned and no bounds are given. Partial compensation warrants a mid score.

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?

The description names a specific verb (reads columns, samples text rows) and resource (a run's table) and clearly distinguishes itself from sibling query_run by noting the metering difference and the fact that no model call is spent. An agent can tell this is an analysis/advisory tool versus a data-fetch tool like sample_rows or query_run.

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?

It gives concrete operating guidance: treat entries as leads, confirm against rows, deterministic ones first, and only add a model source when the person agrees or the brief requested that judgement. It also clarifies it changes nothing and spends no model call, which instructs safe usage. It does not explicitly name when to choose it over an alternative sibling, which keeps it below 5.

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

All Mostly Right 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.

Resources

Need Help?