Algo Trade Analytics

walk_forward_candidate

walk_forward_candidate

Read-onlyIdempotent

Check temporal generalization across non-overlapping walk-forward windows for a required experiment protocolId.

Input Schema

TableJSON Schema

Name	Required	Description
`symbol`	Yes
`endDate`	Yes
`startDate`	Yes
`timeframe`	Yes
`protocolId`	Yes	Experiment protocol id returned by define_experiment_protocol for this exact candidate-evaluation check.
`caseStudyId`	No	Optional: bind this call to one of your case studies. Defaults to the bound run's case study.
`constraints`	No
`windowCount`	No
`researchRunId`	No	Optional: bind this call to one of your existing research runs. Defaults to this session's most recent unfinished run.
`baselineInputs`	No	Optional input overrides as a JSON-stringified object, e.g. '{"SMA Length":14}'. Keys are Pine input names; values are number, string, or boolean.
`baselineSource`	No	Pine source of the comparison baseline. Omit to use the platform benchmark baseline for this scope, which declares 1bp commission per side and 2 ticks slippage so the comparison is not a costed candidate against a zero-cost control.
`evaluationMode`	No
`trainTestSplit`	No
`candidateInputs`	No	Optional input overrides as a JSON-stringified object, e.g. '{"SMA Length":14}'. Keys are Pine input names; values are number, string, or boolean.
`candidateSource`	Yes
`objectiveMetric`	No
`minBarsPerWindow`	No
`mcpIdempotencyKey`	No	Unique key for this logical action. Reuse it only when retrying the same arguments. Required for hosted trust-creating actions when no idempotency header is supplied.
`objectiveDirection`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 17, 2026

addedInput schema / properties / baselineSource / anyOf

Added value: +[
+  {
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / baselineSource / description

Added value: +"Pine source of the comparison baseline. Omit to use the platform benchmark baseline for this scope, which declares 1bp commission per side and 2 ticks slippage so the comparison is not a costed candidate against a zero-cost control."

removedInput schema / properties / baselineSource / minLength
```
Removed value: -1
```
removedInput schema / properties / baselineSource / type
```
Removed value: -"string"
```

changedInput schema / required

Previous value: -[
-  "symbol",
-  "timeframe",
-  "startDate",
-  "endDate",
-  "baselineSource",
-  "candidateSource",
-  "protocolId"
-]New value: +[
+  "symbol",
+  "timeframe",
+  "startDate",
+  "endDate",
+  "candidateSource",
+  "protocolId"
+]

First observedSep 16, 2026

TDQS

B3/5.0

Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the one-sentence read-only framing adds little beyond them. The description does not contradict the annotations, nor does it reveal additional behavioral context such as result contents or whether it requires previously defined protocol artifacts.

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?

The description is a single front-loaded sentence with no filler. Every word earns its place and the core operation is stated immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a high-complexity tool with 19 parameters, 6 required fields, no output schema, and low schema coverage, yet the description provides only a one-line purpose. Critical context such as what happens after the check, how results are returned, and how the walk-forward windows are configured is missing, so the definition is not complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 37% and 19 parameters, the description needed to clarify at least the core required inputs. It only mentions protocolId and does not help with candidateSource, evaluationMode, trainTestSplit, windowCount, candidateInputs, or the objective metric settings, leaving the agent to infer their meaning from names/enums alone.

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?

The description names a concrete verb ('Check') and a distinct resource: temporal generalization across non-overlapping walk-forward windows, with the required protocolId noted. It is specific enough to separate this from generic candidate evaluation, though it does not explicitly contrast with sibling tools such as evaluate_candidate or verify_candidate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

Beyond implying that the tool is for measuring temporal generalization, the description gives no when-to-use guidance and names no alternatives or exclusions. An agent cannot tell from the description when walk_forward_candidate should be chosen over evaluate_candidate, stress_test_candidate, or analyze_overfit_probability.

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

All Algo Trade Analytics 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?