run_revenue_review

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

With no annotations and no output schema, the description carries the full burden and does well: it discloses that the tool returns 16 graded items (🔴/🟡/🟢/ℹ️), and crucially warns that some items are unqualified numerical outputs the host AI must benchmark online against local pricing. That grading legend and the follow-up caveat are exactly the behavioral context an agent needs. It omits any mention of permissions, cost, or rate limits.

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?

A single dense paragraph that front-loads the purpose, then the 16-item breakdown, then the grading legend, then the input modes — a sensible ordering. It is information-heavy but nearly every clause earns its place by carrying inspection criteria or input rules.

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?

For a nested-input, no-annotation tool, the description covers the essentials: what gets reviewed, how results are graded, the two input paths, and the fallback sequence via fast_calc_reports. No output schema exists, yet the grading legend gives enough of a picture of the return shape; only edge-case behavior of the reports object is left implicit.

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 100%, so p_id, stage, and reports are already documented in the schema, including the 'p_id 与 reports 二选一' constraint and the stage default. The description only restates the dual-input structure and adds a light workflow hint (use fast_calc_reports output), so it lands at the baseline 3.

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+resource (收入费用合理性审查 / revenue-and-expense reasonableness review) and quantifies scope (16 items across R/C/X categories), so an agent knows exactly what the tool produces. It does not, however, differentiate itself from overlapping siblings such as run_model_check or run_national_econ.

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?

Explains the two alternative input paths (p_id+stage vs reports object) and gives a concrete prerequisite sequence: when no platform project number exists, call fast_calc_reports first to generate the 11 tables. This is clear input-sourcing guidance with a named sibling, but it stops short of stating when this review is preferred over the other review/analysis tools.

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