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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description adds meaningful context beyond that: it returns raw figures plus a data_ref rather than rendering anything, and states 'Does not show the user a table.' It does not describe failure modes or auth requirements, but the output/behavioral nature is well disclosed.

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 core purpose is front-loaded in the first sentence, and the paragraph covers statement types, row/column structure, dimensions, sibling routing, and chaining without filler. It is slightly dense but each sentence serves a distinct purpose; the alias guidance sentence is the least essential.

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 appropriately explains that results are raw figures and a data_ref, covering return-value expectations. However, for an 8-parameter, 0%-coverage tool with complex financial semantics, the undocumented parameters (scale, decimals, filters, period range) leave the agent under-equipped to invoke it correctly.

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 0% across 8 parameters, so the description carries the full burden. It meaningfully documents statement (P&L/variance/exec summary), scenarios (columns, alias), and dimensions (breakdown by period or cost centre), but leaves scale, decimals, filters, period_start, and period_end entirely unexplained, so roughly half the parameters remain opaque.

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?

States a specific verb and resource ('Run a financial statement — P&L, variance report, or executive summary') and describes the resulting structure (statement lines as rows, scenarios as columns). It explicitly distinguishes its behavior from the display variant by noting 'Does not show the user a table,' so an agent can tell it apart from run_statement and run_metric_data.

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?

Gives a clear routing rule ('For an unspecified general P&L, prefer full_pnl when it is listed by precis_orientation') and a downstream chaining instruction ('pass [data_ref] as data_refs to eval_chart_transform'). It also tells the agent to assign user-facing scenario aliases. It stops short of enumerating when-not-to-use for the other statement types, but the primary selection context is explicit.

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