koalcheck

direction_review_batch

OPERATOR-ONLY. Serve a batch of analyst tweets whose per-ticker direction needs accurate classification, plus the rubric to classify them by.

Candidates = tweets with ≥1 cashtag that have NOT yet been LLM-reviewed. Each item carries the tweet text (fenced as data), its cashtags, and the current heuristic_guess (so you correct rather than start blind). Follow the returned rubric: for EVERY cashtag return one verdict (is_call, direction, confidence, conviction), then call direction_review_submit. Repeat until remaining=0. Read-only and $0 — the classification is done by THIS Claude on the operator's subscription, not by any paid API.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`handle`	No
`include_rubric`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.1/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It declares read-only and $0 operation, explains the batch contents, and clarifies that classification is done by Claude on the operator's subscription. It misses potential details like rate limits or authentication, but is otherwise transparent.

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 description is well-structured with a front-loaded operator warning, clear explanation of purpose, contents, workflow, and cost. It is slightly verbose but every sentence adds value; no redundant information.

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

Completeness5/5

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

Given that an output schema exists, the description adequately covers what the tool returns (tweet text, cashtags, heuristic_guess, rubric) and the workflow. It is complete for a batch processing tool with clear next steps.

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?

Schema coverage is 0%, but the description only implicitly references `limit` via 'batch' and `include_rubric` via 'returned rubric'. The `handle` parameter is not mentioned at all. The description fails to add meaningful context for the parameters, relying on defaults.

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 explicitly states the tool serves a batch of analyst tweets needing direction classification, with a clear distinction from sibling `direction_review_submit`. It specifies the criteria (tweets with ≥1 cashtag, not yet LLM-reviewed) and the inclusion of a rubric.

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?

The description clearly indicates operator-only use and advises to follow the returned rubric and submit verdicts via `direction_review_submit`. It does not explicitly state when not to use the tool or list alternatives, but the context is sufficient for correct invocation.

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

All koalcheck tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0

Disambiguation4/5

Most tools have clearly distinct purposes (e.g., analyst_views fetches views, analyst_debate compares them, analyst_track_record scores accuracy). Some overlap exists between sentiment tools (stocktwits_symbol, ticker_social_sentiment) but descriptions clarify boundaries. Overall, an agent can differentiate them.

Naming Consistency3/5

Naming is mostly lowercase with underscores, but conventions vary: some use prefixes (analyst_, direction_review_), some are single words (quote, leaderboard), and others are verb_noun (score_ticker, screen_stocks). This inconsistency makes patterns less predictable, though prefixes help group related tools.

Tool Count3/5

With 24 tools, the server is slightly above the ideal range of 3-15 for coherence. While each tool seems justified for the financial analysis domain, the volume could be overwhelming. Some tools (e.g., tweet_store_stats, direction_review_batch) are operator-only, reducing the surface for typical agents.

Completeness4/5

The tool set covers core workflows: fetching analyst views, tracking accuracy, SEC fundamentals, insider activity, material events, live quotes, social sentiment, and screening. Gaps like earnings calendar or portfolio management are minor given the focus on analyst-driven analysis. The operator tools for direction review add internal completeness.

Resources

Need Help?