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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description still adds real context beyond them: no sign-in is required, the report is not stored, and only column headers of unrecognized reports may be logged. It does not say what happens when a report format is unsupported (error vs. partial result), which is the remaining behavioral gap.

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?

Each language version is front-loaded with the trigger sentence and avoids filler, but the full text is nearly duplicated across Turkish and English, and within a single version the assistant list (ChatGPT, Perplexity, Gemini) is repeated twice in close succession. The dual-language layout roughly doubles the length without adding information.

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 usefully enumerates what the analysis returns: per-assistant traffic, engagement and conversion rates, revenue, and the largest funnel drop-off versus site baseline. That is enough for an agent to judge applicability. Missing pieces are the unsupported-format behavior and any mention of the language parameter.

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 has to carry the load. It does explain report_text well ('pass the report exactly as exported, as raw CSV text'), which is the key usage constraint. However, the second parameter, language (default 'tr'), is never mentioned anywhere in the description, so an agent has no guidance on whether or how to set the output language.

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+resource: it analyzes an exported traffic source/channel report to quantify traffic from AI assistants, broken down by assistant, engagement, conversion, revenue and funnel drop-off. Scope is far enough from siblings (check_ai_visibility, diagnose_ad_report) that confusion is unlikely, though no sibling is named explicitly.

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?

There is an explicit trigger: 'Use when the user shares an analytics or traffic report and asks how much traffic comes from AI... or whether those visitors buy.' That is clear about when to use it, but it says nothing about when not to use it or which sibling handles adjacent questions.

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