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

Goes well beyond the annotations: discloses that it costs money, which billing path is used depending on budget mode, that the preview states search count and maximum cost, that it requires write actions plus 'Allow actions that spend AI', the 20-actions-per-workspace-per-day quota, and the one-run-per-client concurrency lock. These are exactly the operational facts an agent needs before initiating a spend.

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 purpose and the cost warning arrives before the confirm mechanics, so the critical information is ordered well. It is a single dense paragraph with semicolon-chained clauses, which costs some scannability for a tool with this many caveats, but essentially every sentence carries operational 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?

No output schema exists, and the description compensates by explaining that a preview is returned without confirm and that results are retrieved via get_rankings with lastRun tracking progress. Combined with permissions, quota, concurrency and billing disclosures, an agent has everything needed to invoke it safely.

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 100%, so parameters are already documented; the description nevertheless adds the relational semantics that matter – preview without confirm, confirming with the token from that preview, and keywordIds narrowing to active keywords by default. It doesn't restate the 15-minute/once token expiry beyond the schema, but it reinforces the pairing correctly.

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?

Opens with a concrete verb and resource: check a client's keywords now instead of waiting for the weekly run, with a scope qualifier (all keywords or only the named ones). It is clearly distinguishable from get_rankings (which returns results) and from get_rank_tracking_setup or set_rank_schedule, which don't trigger a run.

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 when-to-use ('now instead of the weekly run'), explicit narrowing option (keywordIds), explicit two-step workflow (preview first, then confirm:true with previewToken), and an explicit follow-up path (get_rankings, lastRun). The only alternative surface it doesn't contrast directly is run_scan, but its scope is clearly keyword rankings.

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