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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the error envelope (a single-element list of {error, ...} with api_error/task_error, dfs_timeout, dfs_unreachable), instructs checking for 'error' before processing results, and notes that an unknown language fails as invalid_language without incurring cost. That cost and failure-mode disclosure is genuinely valuable. Minor remaining gap (no latency/rate-limit or per-request billing details) keeps it from a 5.

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 cap in the first line, then defaults, then error handling. Dense but every clause carries operational information. The mixed German/English phrasing and parenthetical asides add a little friction but don't waste space.

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 4-parameter read-only lookup with an output schema present, the description covers what the agent cannot infer: input bounds, default resolution, accepted value formats, and error shapes to screen for. Nothing needed to call it correctly is missing.

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?

Critical, because schema description coverage is 0%. The description fully compensates: keywords is capped at 1000 items; location accepts DataForSEO location names, 'City,Region,Country' forms, ISO codes, and German country names; language accepts ISO codes or language names with a defined failure mode; workspace is a slug that is optional when only one workspace exists.

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?

Names a specific verb+resource: Search Volume and CPC for a keyword list (max 1000), sourced from Google Ads data. An agent can tell this is a bulk metrics lookup rather than research/ideas. It doesn't name sibling alternatives such as dfs_keyword_overview or dfs_keyword_suggestions to draw the boundary, which keeps it from a 5.

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?

Usage is implied by the input shape (a keyword list in, metrics out) and the 1000-keyword cap clarifies the batch scenario, but there is no explicit 'use this instead of X when Y' guidance among the many dfs_keyword_* siblings. Defaults for location/language from the workspace is useful context but is parameter behavior, not when-to-use guidance.

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