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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile, so the bar for the description is lower. The description adds meaningful behavioral context beyond annotations: the 2-5 stock input constraint and the complete list of 12 returned metrics, giving the agent a concrete expectation of output content.

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?

Three sentences, each earning its place: what it does, what it returns, and when to use it. The purpose is front-loaded in the first sentence, and although the field list is long, it is information-dense and directly useful to the agent.

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 compensates by explicitly listing all returned metrics. Input constraints, parameter formats, and usage examples are all present; only minor gaps remain, such as behavior for invalid or non-existent ticker symbols and data freshness, which are relatively unimportant for a single-parameter read-only comparison 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?

Schema description coverage is 100%, with the symbols parameter fully documented for both CSV string and array formats, so the schema carries the semantic burden. The description only restates the 2-5 range already in the schema and adds illustrative query examples, which is baseline value rather than new parameter meaning.

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 opens with 'Compare 2 to 5 stocks side by side' — a specific verb, resource, and range constraint. The enumerated return fields (price, P/E ratio, dividend yield, beta, etc.) go beyond what a single-stock quote tool would offer, making the purpose unambiguous and distinguishing it from siblings like stock_quote and stock_quote_batch.

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 provides explicit example queries ('compare Apple and Microsoft', 'which is a better investment, NVDA or AMD?') and closes with 'any stock-vs-stock analysis', which gives clear context for when to use it. However, it never names alternative tools or states when not to use it (e.g., for a single stock quote or price history), stopping short of a full when/when-not treatment.

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