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

Annotations only say readOnly=false, idempotent=false, destructive=false, so the description carries the disclosure burden and does it thoroughly. It reveals that the tool crawls, writes AI recommendations, probes external engines, checks SERP, charges credits, enforces one concurrent run, can take hours, and that results must be fetched via the report tool. This is rich, non-obvious behavioral context beyond any structured field.

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?

The description is long but every sentence carries operational value: scope, engines, cost model, concurrency, duration, and result retrieval. It is front-loaded with the core purpose, then layers constraints and follow-up. No filler or restatement of the tool name.

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 complex, side-effectful, cost-incurring tool with no output schema and minimal parameter docs, the description covers what the tool does, what it costs, how long it may take, its concurrency limit, and exactly where to get progress/results. An agent has enough information to invoke it correctly and manage expectations.

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 50%: websiteUrl is documented, workspaceId is not. The description compensates by stating websiteUrl defaults to the workspace's saved URL and repeatedly references workspace scoping ('the workspace's website', 'one concurrent run per workspace'), letting the agent infer workspaceId selects the target workspace. It adds meaning beyond the schema but does not fully spell out workspaceId semantics.

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 specific action and resource: 'Start an SEO & AI-visibility audit of the workspace's website.' It names the concrete scope (30 pages, ruleset, AI assistants, SERP) and differentiates itself from the reporting sibling by pointing to campaignstack_seo_get_latest_report for results.

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?

The description clearly states when this is the tool to call: when starting a website audit. It also gives practical constraints around concurrency ('One concurrent run per workspace'), cost, and follow-up polling. It does not explicitly enumerate when-not-to-use alternatives like campaignstack_analyze_website or campaignstack_seo_get_advisory, but the context is clear enough.

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