dividend_history_deep

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

With no annotations, the description carries the burden of disclosure. It explicitly lists what the tool returns (full history up to 60 entries, annual totals, trailing yield, total dividends), but it does not mention potential errors, data source reliability, rate limits, or any side effects. The tool is clearly a read operation but this is not explicitly stated.

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 with a one-line summary, a rationale note, a bullet list of outputs, argument details, and examples. The Bloomberg/FactSet note is slightly extraneous but still relevant; otherwise every sentence earns its place.

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?

The description covers purpose, return values, parameter format, and examples. An output schema exists, so detailed return structures are not needed. It could be more complete with notes on error handling or invalid symbols, but for a single-parameter data retrieval tool it is quite thorough.

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 for 'symbol', but the description fully compensates by explaining it as 'NSE or global stock symbol' and providing examples (RELIANCE, TCS, INFY, AAPL). This gives the agent exactly the information needed to invoke the tool correctly.

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 '10-year dividend history with yield calculation and annual summary' and lists specific outputs including full dividend history, annual totals, trailing yield, and total dividends. This differentiates it from sibling tools like 'dividend_history' by emphasizing the 'deep' 10-year scope.

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 mentions that Bloomberg and FactSet charge for deep dividend history while yfinance is free, and the name 'deep' implies longer history, but it does not explicitly compare with the sibling 'dividend_history' tool. No clear guidance on when to choose this versus the simpler alternative is provided.

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