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

Goes far beyond the readOnly/openWorld annotations: discloses LinkedIn-side approximations for privacy, suppression of values with fewer than 3 events, up to 24h data latency, a 2-year retention window, and the critical caveat that row sums do not equal account totals. These are exactly the behavioral traits that would otherwise cause misinterpretation.

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 purpose sentence followed by labeled parameter blocks and a clearly separated limitations block — easy to scan. Dense but every line carries information; only minor trimming (e.g. the German per-row field list given an output schema exists) would improve it.

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?

Covers what an agent needs to call this correctly: dimension choice, timeframe, campaign scoping, row limit, and the interpretation caveats. Even though an output schema exists, it briefly names the per-row metrics (name, urn, impressions, clicks, cost, conversions, leads, lead_form_opens), which helps the agent reason about results.

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 description coverage is 0%, so the description must carry the load and it does: valid dimension values, timeframe syntax (date_from/date_to or days), campaign_ids cap of 20 plus the requirement that they belong to the workspace ad account, limit max 100 with impression-based sorting, and the optional workspace slug.

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?

Opening sentence states a concrete verb/resource and scope: performance of LinkedIn ads broken down by professional demographics ('Wer hat die LinkedIn-Anzeigen gesehen und geklickt'). The enumerated dimension list (job_function, seniority, industry, company_size, job_title, company, country, region) makes it unmistakable versus sibling tools like linkedin_campaign_performance or linkedin_creative_performance.

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?

Explicitly routes the agent: use linkedin_performance_report (level=account) when correct aggregate totals are needed, because row sums here are non-additive. It also states when campaign_ids should be used ('optional auf diese Kampagnen einschränken ... sonst ganzes Konto') and when workspace can be omitted.

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