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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real context such as 'synchronous' execution, 'task support: forbidden', and 'no publication authority', plus explicit output-handling rules (use assistantSummary first, never dump raw JSON, mention IDs only when useful). This is meaningful behavioral guidance beyond the structured fields.

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 opening sentence duplicates the title verbatim, and 'Classification: read-only. Execution: synchronous. Task support: forbidden.' restates annotation-covered facts. The single most useful piece of routing information ('deprecated alias') is buried in the middle rather than front-loaded, and the response-style rules sprawl across multiple sentences.

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 explained and the output-presentation guidance is a bonus. But for a tool with 20 inputs, 0 required, nested objects, and 0% parameter documentation, the description provides no help on how to actually populate the call, which is the largest completeness gap.

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?

Twenty parameters with 0% schema description coverage and no enums, yet the description names none of them and explains no semantics, formats, or required combinations. 'Advertiser-scoped' and the mention of IDs are the only faint hints (advertiserId, entity/eventId/opportunityId), which is far from compensating for the coverage gap.

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 states a specific verb+resource ('Read advertiser-scoped World Intelligence V3 decision with evidence') and explicitly identifies itself as a deprecated alias for get_world_research_decision, which differentiates it from the many sibling get_world_research_* tools. The only weakness is that the same sentence is duplicated verbatim from the title, adding no new information.

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?

Calling itself a 'deprecated alias for get_world_research_decision' implicitly routes the agent toward the canonical sibling, which is useful. However, it never states an explicit rule ('use get_world_research_decision instead' or 'only retained for backward compatibility'), and it gives no guidance on when this tool should ever be chosen over its canonical counterpart.

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