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

Annotations already cover readOnlyHint/idempotentHint/destructiveHint/openWorldHint, so 'Classification: read-only' is redundant. The description does add genuinely non-annotation context: synchronous execution, task support forbidden, and the fact that the payload is internal orchestration state rather than user-facing content. That materially changes how an agent handles the result.

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 purpose is front-loaded and the text is not bloated, but the title is restated almost verbatim (including a doubled period and a repeated 'no publication authority'), and several sentences are generic presentation policy that belongs in a system prompt rather than a per-tool definition. Size is acceptable; signal-to-noise is only fair.

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?

An output schema exists, so return values need not be described, and the assistantSummary pointer is a useful hook. However, for a 20-parameter, nested-object, zero-required tool with no schema descriptions, the definition gives no help on which inputs to supply or what a 'decision with evidence' requires, so an agent cannot reliably invoke it.

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?

There are 20 parameters (entity, question, advertiserId, seatId, targetMarkets, locale fields, nested marketContext) at 0% schema description coverage, and the description explains none of them. With essentially no structured documentation, the description needed to carry the parameter burden and it does not, leaving key inputs like entity vs question vs marketContext completely undefined.

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?

The description names a specific verb and resource ('Read advertiser-scoped World Intelligence V3 decision with evidence') plus a scope qualifier (advertiser-scoped) and a boundary ('no publication authority'). That is enough to distinguish it from write-side siblings like build_world_research_profile or run_world_intelligence, but it never names or contrasts the close read-side siblings (get_world_research_summary, get_world_research_proposal, leanriq_get_world_research_decision), so borderline ambiguity remains.

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 guidance present is about how to present results ('Use assistantSummary first', 'Never display raw JSON...', 'suggest the next best LeanrIQ action'), not about when to call this tool versus its many siblings. There is no condition, trigger, or alternative named, so an agent has no selection guidance.

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