stock_extended_hours

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

No annotations are provided, so the description fully bears the burden of behavioral disclosure. It explains that during the regular session, post_market will be null; on weekends/holidays, it returns the most recent data. It details the computed changes (change_vs_previous_close_pct, change_vs_regular_close_pct) and the return structure. This gives a comprehensive understanding of the tool's behavior without contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the purpose. It uses bullet points for return values, making it easy to parse. Every sentence adds value, explaining usage scenarios, session behavior, and computed fields. It is concise given the necessary detail.

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

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

With no output schema, the description thoroughly explains the return format (pre_market, regular, post_market with fields and nullable states) and contextual fields (previous_close, currency, exchange, market_state). It covers edge cases (regular session null, weekends/holidays) and the meaning of each computed percentage change. This is complete for a single-parameter tool.

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

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

The input schema has 0% description coverage, but the parameter description in the tool description adds significant meaning: 'symbol: US stock symbol — AAPL, NVDA, TSLA, SPY, ^GSPC, etc.' This clarifies acceptable values. However, it could specify whether case matters or include additional format details, which prevents a perfect score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides 'Real-time pre-market and after-hours prices for a US stock symbol.' It specifies the verb (get real-time prices) and resource (extended hours data). The purpose is distinct from siblings like stock_prices (regular hours) and yahoo_price, as it explicitly focuses on pre-market and after-hours sessions.

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

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

The description explicitly says 'Use this when the user asks about a stock outside the regular 9:30am-4pm ET session' and gives concrete examples: earnings reactions, overnight news, 'what is X doing in after-hours?', 'how did Y open in pre-market?'. It also clarifies when not to use (regular hours). This provides clear guidance for an AI agent.

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