Financial Statement (SEC)

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

Going well beyond the readOnlyHint/idempotentHint/openWorldHint annotations, the description discloses the provenance mechanism, how derived values are tagged, that values are raw currency units, and the default period behavior. An agent can anticipate the exact return characteristics before invoking the tool.

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 dense sentences with no filler. The core purpose is front-loaded, and each sentence adds a distinct value: source identity, provenance behavior/units, and default tuning guidance.

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?

Given the existence of an output schema and strong annotations, the description supplies everything an agent needs to call correctly: what data is returned, how to cite it, the raw-unit caveat, and default/expansion behavior. Nothing critical is left unexplained.

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 already covers all 5 parameters, but the description adds meaningful context: provenance attaches citeable SEC sources, derived values carry two-term derivations, values are raw units, and latest_n/period_type interact with a 5-annual default. This is above the baseline high-coverage score, though the schema still carries most naming and enum semantics.

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 a specific, verb-like resource: 'As-reported financial statement for a US stock, assembled straight from SEC inline-XBRL.' This clearly distinguishes it from derived or valuation-style siblings like get_fundamentals and get_key_metrics by foregrounding the SEC/as-reported nature.

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 gives parameter-level guidance ('Defaults return the latest 5 annual periods; widen period_type/latest_n only when the question needs more history') and recommends keeping provenance on for citeable answers, but it never states when to prefer this tool over siblings such as get_fundamentals or get_notes. The use case is implied by 'as-reported,' not explicitly routed.

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