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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds synchronous execution, forbidden task support, no publication authority, and concrete output-handling rules: use assistantSummary first, do not show raw JSON, and mention IDs only when useful. 'Classification: read-only' repeats the annotation, but the operational context goes beyond 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 purpose and deprecation status are front-loaded, and the operational sentences are terse and useful for an orchestrator. There is minor redundancy between the title, description, and annotations around read-only classification, but the text is not bloated.

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 less explanation, and annotations carry the safety profile. However, for a 20-parameter input schema with no parameter descriptions, the description completely omits input semantics, leaving an agent unable to know how to scope or filter mentions correctly.

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?

The schema has 20 parameters with 0% description coverage, and the description provides no parameter-level meaning for limit, entity, seatId, advertiserId, locale fields, market context, or any other input. 'Advertiser-scoped' faintly hints at advertiserId, but this is nowhere near sufficient for correct invocation.

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?

It states a specific verb, resource, scope, and qualifier: read advertiser-scoped World Intelligence V3 mentions with evidence. It also explicitly names the canonical sibling get_world_research_mentions and labels itself a deprecated alias, so an agent can distinguish it from other world-research tools without opening a schema.

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 deprecation note and the named replacement get_world_research_mentions give clear usage steering, and 'no publication authority' sets a read-only boundary. However, it does not explicitly state when this alias is still appropriate or how to choose between it and related tools such as get_world_research_insights.

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