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

Annotations alone (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) would leave an agent puzzled about why a read looks like a write; the description explains this by disclosing that the call consumes one read and persists the result to the user's Puley history. It also reveals the upstream provider (Yahoo Finance) and that quote timestamps are returned. It does not say whether prices are real-time or delayed, which is the main remaining gap.

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 front-loaded with the payload and its source, then narrows to the single argument, then to cost/persistence. It is dense but every clause carries information; the returned-field list is long but necessary because no output schema exists.

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 a 0%-covered single parameter and no output schema, the description compensates on both fronts — it fully specifies the argument and enumerates the returned fields (price, session change, day and 52-week range, volume, exchange, quote time). Only the real-time vs delayed nature of the feed is left unaddressed.

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?

Schema description coverage is 0%, so the description must carry the parameter alone, and it does: cardinality (up to 10), delimiter (comma-separated), three symbol dialects with concrete examples (AAPL, NPN.JO, ^GSPC, EURUSD=X, BTC-USD), and the fallback of company/asset names. This is more than the bare schema could convey.

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 names the specific resource (live quotes for shares, ETFs, indices, currencies, crypto) and the exact data source (Yahoo Finance), so an agent knows precisely what it returns. The asset-class enumeration also separates it from narrower siblings like drug_prices, resale_prices, or subscription_prices.

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?

It supplies concrete invocation context — max 10 comma-separated symbols, accepted symbol formats per exchange, and that plain names (Apple, bitcoin, gold) also work — plus a cost signal ('Uses one read'). It stops short of stating when to prefer a sibling such as local_stock or app_charts, so there are no explicit exclusions.

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