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

Annotations already declare a safe read-only, non-destructive, closed-world operation, so the safety burden is lifted. The description adds genuinely new behavioral context beyond that: the return is a formatted table with structured data, the widget already renders it to the user, and the agent should interpret rather than echo the table. What it does not disclose is error behavior or how large a breakdown it can handle.

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?

Front-loaded with the core purpose and examples before moving to invocation and output guidance, so the most important information lands first. The closing sentence about not reproducing the table is long but earns its place as an output-behavior instruction; overall there is little waste.

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 usefully defines the table's row/column structure, which covers the return-value gap. However, for an 8-parameter tool with 0% schema description coverage, the description leaves most inputs (filters, period bounds, scale, decimals) unexplained, so an agent cannot fully invoke it from the definition alone.

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 must carry parameter meaning itself. It does add real semantics for `scenarios` (array of objects, each needing a user-facing alias) and implies `dimensions`/`metrics` via the row/column description, but `scale`, `decimals`, `filters`, `period_start`, and `period_end` are left entirely undefined in both schema and description.

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 ('Break one or more metrics down by a dimension') and reinforces it with four concrete examples (revenue by project, utilisation by employee, headcount trends, GL account drill-down). The output shape ('rows are the dimension; columns are metrics × scenarios') further pins down what the tool produces. It never names or contrasts a sibling such as run_metric_data, so differentiation from the closely named data variant is left to inference.

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 actionable invocation guidance ('Pass `scenarios` explicitly and give every scenario a concise, user-facing `alias`') and one conditional output rule ('unless the user explicitly requests it or the widget is unavailable'). It does not state when to reach for this tool versus run_metric_data or run_statement, so the routing decision remains implied.

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