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

Annotations already declare readOnly/idempotent/no-destructive behavior, so the description earns credit for adding the Scale plan prerequisite and explaining the temporal evolution of narrative data. It still does not describe return shape or pagination, but the added plan requirement is meaningful behavioral context.

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 description is front-loaded with a short concept explanation followed by a compact Args list. It is efficient and readable, though the Args list partly repeats schema information rather than adding purely new detail.

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?

For a read-only tool with no output schema and five parameters, the description explains the concept and most inputs but does not describe what data is returned or its shape. It also omits user_intent from the narrative text, leaving the output contract underspecified.

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?

With only 20% schema description coverage, the description does useful work: it documents brand_id as required, narrative_id as optional, include values ('snapshots', 'correctives'), and days as a 7-365 lookback with default 90. It omits user_intent from the text, but that parameter already has schema-level description.

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 and resource ('Get narrative intelligence data') and clarifies the concept: tracking topics/storylines across AI models over time. It does not explicitly distinguish itself from siblings like get_perception or get_visibility_scores, so it misses full differentiation.

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?

It gives context for when narratives are useful and notes the Scale plan requirement, but it does not state when-not to use this tool or name alternative tools for overlapping needs. Usage is implied rather than directed.

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