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

Annotations only declare readOnlyHint and openWorldHint, and the description goes well beyond that: chat_gpt data is US/English only and passed location/language values are silently ignored, payloads are capped at 10 keywords, billing is pay-as-you-go, and errors arrive as a one-element list [{error,...}] with named codes (api_error/task_error, dfs_timeout, dfs_unreachable, invalid_platform) that must be checked before evaluation. That is precisely the silent-override and failure-mode information an agent needs.

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?

No filler sentences — purpose, platform constraint, caps, billing, return shape, error handling, workspace — and the purpose question is front-loaded. It is however a dense block of transliterated German with several constraints stacked into one paragraph, which costs some scannability even though nothing is wasted.

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, open-world DataForSEO call with 6 undocumented parameters, the description covers cost, platform limits, parameter defaults, row-level return semantics and the error envelope — enough to invoke it correctly and to post-process the result. An output schema exists, so the fact that return values are only sketched rather than fully enumerated is not a gap.

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 carry the burden and it does: 'limit' is explained as the max row count of the response, 'keywords' as capped at 10 per call, 'platform' as google (default, AI Overview) or chat_gpt with its US/English restriction, 'location'/'language' default to the workspace and follow dfs_keyword_volume's format, and 'workspace' is optional when only one workspace exists. Every one of the six parameters gets meaning the schema does not provide.

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 opening line gives a specific verb+resource combination ('Wo/wie werden diese Keywords in KI-Antworten erwaehnt bzw. zitiert?') and the return-format sentence pins down the unit of output (one row per prompt/source, citation vs mention). It is clearly distinguishable from generic SERP or keyword tools, though it never names the adjacent dfs_llm_mentions_metrics or dfs_llm_responses tools, so sibling disambiguation is left implicit.

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?

Explicit operational guidance: one call covers exactly one platform, so call twice for both; 'chat_gpt' is limited to United States/English with location/language auto-forced; max 10 keywords per call; pay-as-you-go with a structured hint on error 40204. It does not state when to prefer this over dfs_llm_mentions_metrics/dfs_llm_top_domains, which keeps it out of 5 territory.

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