financial_statements

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

The description goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the source waterfall, inline ratio/CAGR/projection computation, the mechanical nature of the projection, and the structured not_available response instead of bare nulls. This is rich behavioral context that annotations do not provide.

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 primary purpose and waterfall, then packs the important caveats into compact, purposeful clauses. Every sentence adds value: return shape, projection labeling, fallback sources, and null handling. No filler or repetition of schema details.

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 correctly explains the return type, projection behavior, and failure mode, referencing ratio_analysis for shape. It is slightly incomplete regarding coverage nuances for unlisted vs. global companies and exact date-range handling, but it is comprehensive enough for most invocation decisions.

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?

With 50% schema coverage, the description partially compensates by adding conditional detail about includeRatios ('computed inline by default whenever 2+ historical periods are available'). However, it does not clarify the required context object's role in the source waterfall or explain how fields like listed, country, or sector influence behavior, leaving a gap for the required parameter.

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 uses a specific verb ('Retrieves') and names the exact resource ('financial statements'), then details the source waterfall. It also distinguishes itself from siblings by noting that ratio_analysis consumes its output and that dcf_valuation/scenario_analysis handle assumption-driven fair value, so an agent can tell it apart without inspecting schemas.

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 clearly signals when this tool is appropriate: when financial statements are needed, and it routes fair-value work to dcf_valuation/scenario_analysis. It does not explicitly say when not to use it or name a direct alternative for the same statements, but the context is strong enough to guide selection.

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