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

Annotations already declare this a safe, idempotent, non-destructive read, so the bar is lower. The description nevertheless adds genuinely useful behavioral context: results are bounded by differing observation times and missing metrics, warning the agent that conclusions are approximate rather than authoritative.

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?

Two sentences, zero filler. The operation and its subject come first, and the reliability caveat is placed after the action rather than padding the opening.

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?

Safety is covered by annotations and return shape by the output schema, so those gaps don't count. What is missing is the practical context an agent needs to call it correctly: that targets must be saved intelligence targets for that brand and that metrics must have been observed first.

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 the description carries the burden, and it does partially: it clarifies that targetIds are tracked sources belonging to the given brand and that the count is two or three. It still says nothing about the brandId/targetId formats or the brand-to-target ownership requirement beyond a bare implication.

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: comparing saved public metrics across two or three tracked sources for a brand. That is enough for an agent to understand the operation, though it never names or distinguishes itself from siblings like get_intelligence_target or scan_intelligence_target.

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?

There is no when-to-use guidance, no prerequisites (targets must already be tracked/saved and presumably scanned), and no routing to alternatives such as fetching a single target's metrics. The 'two or three sources' constraint is restated from the schema rather than offered as selection advice.

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