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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the data provenance (Yahoo Finance via yfinance, no API key), the volume/shape of results (up to 4 years annual or 4 quarters, transposed by reporting period), and the 'trailing is income-only' constraint. These are genuine additions, though the transposition detail partially overlaps an existing output schema.

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?

Front-loaded with the core action, then a scannable bullet list, then option/format quirks, then source attribution. Every block earns its place, though the option lists in the body duplicate the schema's field descriptions and could be trimmed.

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?

An output schema exists, so return-value explanation is not strictly required, yet the description still characterizes result volume and orientation. Combined with provenance and the frequency caveats, an agent has enough to call this correctly; the unexplained auxiliary filter params are the remaining gap.

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 reported at 0%, but the description compensates only for the two user-facing params, restating the 'statement' and 'freq' option sets that the schema's own field descriptions already enumerate. The many auxiliary params (mcp_prompt_id, wholesaler_ids, source_resource_id, exclude_fillers, etc.) are neither explained nor hinted at, and the trailing/TTM income-only caveat is the single piece of real added 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 first sentence names a specific verb (Fetch) and resource (income statement, cash flow statement, balance sheet for a stock), which is unambiguous. It does not explicitly name or contrast with siblings such as GetEarningsHistory or GetDividendsAndSplits, so differentiation is left to the agent.

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 'Use this tool when:' block gives four concrete triggers (revenue/EPS, cash flow/CapEx, assets/debt/equity, fundamental analysis), which is strong positive guidance. It provides no when-not conditions and names no alternative tool, so it stops short of a 5.

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