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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds far more: the copy is read from two public sources with named `ad_copy_source` values, the Posts API is explicitly unavailable, the rate-limit signature (`ad_copy_status: "ad_library_rate_limited"`) and its meaning, null-vs-false semantics for author fields, and anti-fabrication rules. This is rich behavioral context beyond structured data.

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?

Front-loaded with the core purpose and inputs before the operational caveats, and nearly every paragraph carries actionable detail (obtaining copy, rate limits, null semantics). It is on the long side and the return-field enumeration overlaps with the output schema, but it does not descend into filler.

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?

Given a mutating-free read tool with an output schema present, the description covers everything an agent needs: input format, source of data, rate-limit handling, null semantics, and fallback behavior when copy is missing. Nothing required to invoke or interpret it correctly is absent.

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?

Schema coverage is 0%, so the description must compensate, and it largely does: `creative_ids` (urn:li:sponsoredCreative:N or bare N, comma-separated, max 60) and `post_urns` (urn:li:share:N / urn:li:ugcPost:N) are given syntax and format. The required `account_id` is never explained, leaving one gap in otherwise strong parameter documentation.

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?

States a specific verb+resource ('Reads the actual AD COPY of specific LinkedIn ads') and frames the analytical purpose ('which messaging performs best'). It clearly separates itself from siblings like list_linkedin_creatives (metadata) and linkedin_campaign_analytics (metrics), telling the agent exactly what unique artifact it returns.

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?

Explains when to use it (messaging-performance analysis), where to source the ids (top pivotValues from linkedin_campaign_analytics pivot=CREATIVE), and gives explicit batching guidance ('ask for the TOP rows (10–20 creative_ids), not the whole account') with the failure mode (HTTP 429, minutes-long window). This is exactly the when/when-not/alternatives coverage the dimension rewards.

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