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

Without annotations, the description carries the burden. It discloses that the tool returns raw figures and a `data_ref`, and instructs to pass the `data_ref` to `eval_chart_transform`. It also says it does not display a table. This covers key behavioral traits, though it omits details on idempotency, side effects, or error conditions.

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 coherent paragraph of 5 sentences, efficient without wasted words. It could benefit from bullet points or clearer separation of purpose, usage, and parameters, but remains concise for a first read.

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 tool's complexity (13 parameters, no annotations, no output schema), the description is insufficient. It covers high-level purpose and a few usage hints but fails to document the majority of parameters, return structure beyond raw figures, or behavior under different statements/errors. An agent would struggle to invoke it correctly without additional context.

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 coverage is 0%, so the description must compensate but only lightly touches on parameters: it mentions 'optional dimension breakdown' (likely `dimensions`) and hints at scenarios needing an `alias`. The other 11 parameters (scale, layout, target, filters, decimals, filename, overwrite, statement, period_end, sheet_name, period_start) are not explained, leaving the agent guessing.

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 runs financial statements (P&L, variance, exec summary) with rows as statement lines and columns as scenarios. It distinguishes from siblings like `full_pnl` by mentioning preference for that tool when listed by `precis_orientation`, and from `run_statement` implicitly by returning raw data and a `data_ref` for analysis/chart rather than showing a table.

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?

Provides guidance to prefer `full_pnl` for unspecified general P&L when available, indicating when not to use this tool. Also notes it does not show the user a table, implying it is for data extraction. However, it lacks explicit exclusion of alternatives like `run_statement` or `run_metric_data`.

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