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

With no annotations provided, the description carries the full disclosure burden. It reveals key behavioral traits: exclusion of later restatements by construction, reporting of whether each period has been restated and its current value, and the currency assumption (millions of filing's own reporting currency). These go beyond simple 'returns financials' and are critical for safe usage.

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 a single dense paragraph with each sentence serving a purpose. It front-loads the core purpose, then explains the restatement avoidance, current view behavior, and currency handling. No superfluous words.

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 tool has 7 parameters and no output schema. The description covers the main use case (backtesting), as_of semantics, restatement disclosure, and currency. However, it does not explain the remaining parameters or the return structure beyond the restatement flags. Given the complexity, this is a minor gap; overall context is adequate.

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 only 14% (only ticker has a description). The description adds meaning only for as_of ('Omit as_of for the current view') but leaves consol, indfmt, popsrc, datafmt, and periods entirely unexplained. Given the low schema coverage, the description should compensate more, but it does not.

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 the tool returns 'as-FIRST-REPORTED quarterly financials for a ticker' as of a given date, using a specific verb ('returns') and resource. It distinguishes itself from ordinary financials endpoints that serve restated views, which is a clear sibling differentiation.

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?

It explicitly states when to use this tool: 'safe to backtest on' because restatements are excluded. It also contrasts with 'ordinary financials endpoints' that 'will leak look-ahead', providing a clear when-not. Additionally, it gives a usage instruction: 'Omit as_of for the current view.'

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