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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so 'Classification: read-only' largely repeats them. The description nevertheless adds context beyond the annotations: synchronous execution, task support forbidden, and substantial output-handling behavior (JSON is internal application state, use assistantSummary first, never display raw JSON, mention IDs only when useful).

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 definition opens with a verbatim duplication of the title, then the deprecation note, then execution metadata, then a long run-on block of output-presentation rules. The deprecation note and output guidance earn their place, but the front-loaded repetition and density of boilerplate reduce clarity.

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?

Because an output schema exists, return values need not be explained, and the description covers output handling reasonably well. But for a 20-parameter tool, it says nothing about how any parameter should be supplied, which is a serious completeness gap despite the read-only, deprecated nature of the tool.

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 with 0% schema description coverage, so the description is the only place parameter meaning could be supplied - and it provides none. Candidates like advertiserId, question, seatId, targetMarkets, and marketContext are left entirely to the reader. The schema's types and constraints give minimal footing, but the description adds no semantic value.

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 first sentence states a specific verb+resource ('Read advertiser-scoped World Intelligence V3 question with evidence') and a boundary ('no publication authority'). It also identifies itself as a deprecated alias for get_world_research_question, which helps separate it from that sibling. It stops short of 5 because 'question with evidence' remains somewhat abstract.

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?

Naming the tool a 'Deprecated alias for get_world_research_question' implicitly steers an agent toward the non-deprecated sibling, which is the most important consumption guidance here. However, there is no explicit when-to-use / when-not-to-use statement or a direct instruction to prefer the canonical tool. Usage is only implied.

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