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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the bar is lower, and the description still adds real behavioral content: result bounds and, importantly, that approval requirements are configurable by the org admin while business workflow approvals always apply. What is missing is any disclosure of failure modes or what happens when a report definition is invalid.

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?

Three short sentences, front-loaded with the core action and with no filler. The approval sentence is slightly verbose relative to its value but still conveys meaningful policy context.

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?

This is a complex tool with a deeply nested, entirely undocumented request object, and the description delegates the payload shape to get_report_registry rather than explaining it. It benefits from an output schema, so return values need no explanation, but the delegation leaves the call contract incomplete without a second lookup.

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%, so every nested field (definitionId, baseEntity, filters, sorts, columns, pageSize) is undocumented in structured data. The description partially compensates by routing the agent to get_report_registry, but it does not itself explain the definitionId vs baseEntity distinction or filter operator semantics.

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 bounded read-only report') and implies pagination via 'bounded'. It does not explicitly distinguish itself from nearby siblings such as export_report, get_report_metrics, or get_saved_report, so an agent must infer that this executes rather than exports or aggregates.

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?

The description gives a concrete procedural pointer ('Consult get_report_registry for the exact request shape'), which is useful context for calling it. However, it never states when to use this versus export_report or get_report_metrics, nor any precondition like 'a report definition must already exist'.

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