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

Beyond the supplied annotations (readOnlyHint=true, openWorldHint=false, destructiveHint=false), the description adds the behavior an agent actually needs: no sign-in is required, the report is not stored and is processed only for this request, and only column headers of unrecognized reports may be logged. Those retention and logging disclosures are exactly the kind of context annotations cannot carry.

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?

Content is front-loaded with the purpose before the input instructions, which is correct ordering. The main cost is that the entire description is duplicated verbatim in Turkish and English, roughly doubling length without adding information for a given reader; the bilingual approach is defensible but is not concise.

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?

With no output schema, the description carries the burden of describing returns, and it does: wasted spend, priority campaign with reason, and last-7-day trend when a daily breakdown exists. Gaps remain around output format/structure, what happens when a report is unrecognized or unsupported, and the semantics of the language and platform parameters.

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 compensate, and it does well for the single required parameter report_text by specifying raw CSV, unmodified export, no table conversion and no column removal. However, the two optional parameters language and platform receive no explanation at all — platform is only implied by the list of supported ad platforms, and language is never mentioned — leaving real ambiguity.

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 names a specific verb (diagnoses) and resource (a campaign report exported from Meta Ads, Google Ads, TikTok Ads or ChatGPT Ads), then enumerates the concrete findings it returns: spend with no sales/conversions, the campaign to inspect first plus the reason, and a 7-day trend. That level of specificity clearly separates it from the sibling tools check_ai_visibility and check_site_measurement, which address entirely different resources.

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 clear operational guidance for invocation: pass the report exactly as exported, as raw CSV text, into report_text, and explicitly warns against converting to a table or dropping columns. What it does not do is state when to prefer this tool over alternatives or any preconditions (e.g., which report granularity is required for the 7-day trend to appear).

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