Manawa Terminal

Run DeepDive analysis

run_deepdive

Queue a full DeepDive suite for a stock using a monthly custom-run grant.

Prepaid search credits cannot pay for this. Free plans have 0 runs;
Basic has 10/month; Pro has 50/month. Re-running a ticker already
unlocked this month does not consume another grant. The call returns
as soon as the job is queued — do not poll.

Args:
    ticker: Stock symbol (e.g. "AAPL")
    force: Re-queue every chapter even when a current report exists.
        Use when on-file content is the wrong instrument (e.g. ZS
        Thesis written as soybeans).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`force`	No
`ticker`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 16, 2026

addedInput schema / properties / force

Added value: +{
+  "default": false,
+  "title": "Force",
+  "type": "boolean"
+}

AddedAug 17, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial behavioral detail beyond annotations: the call is async (returns when queued, do not poll), it consumes a monthly grant, and prepaid credits are rejected. Annotations (readOnlyHint=false, destructiveHint=false) are consistent with a side-effecting but non-destructive queueing tool — no contradiction.

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?

Well front-loaded: purpose, then billing/quotas, then async behavior, then args. All sentences earn their place, especially the concrete force example. Slightly long at ~100 words, but the quota breakdown and re-run nuance justify the length for a tool with billing implications.

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?

Covers everything needed to invoke correctly: quotas, billing exclusions, async return behavior, force semantics, and parameter enrichment. The output schema covers return values. Minor gap: no mention of where completed results are delivered, though the 'do not poll' note mitigates the uncertainty.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates: ticker gets format and example ('AAPL'), and force gets precise semantics ('Re-queue every chapter even when a current report exists') plus a concrete when-to-use example (ZS thesis written as soybeans). This far exceeds the bare schema titles.

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?

Opens with a specific verb-resource-scope: 'Queue a full DeepDive suite for a stock using a monthly custom-run grant.' This adds queueing behavior and the grant mechanism beyond the title, and no sibling tool queues analysis runs, so it is clearly differentiated.

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?

Gives explicit when-to/not-to-use context: prepaid search credits are excluded, plan quotas are spelled out (Free 0, Basic 10, Pro 50), and re-running an already-unlocked ticker consumes no grant. It does not name an alternative sibling, but no sibling closely overlaps this action.

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

All Manawa Terminal 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?