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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond that: the data source scale (4.4B edges, 120M domains), the ranking method (CrawlGraph authority), and a cost note ('One call = one quota credit'). These details help the agent understand operational implications, earning a 4.

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 three sentences: the first states the core function, the second lists use cases, and the third adds a cost note. It is front-loaded with the essential purpose and avoids redundancy. It is not overly verbose and earns every sentence, though it could be tightened by removing the use-case list, but it is still efficient.

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?

Given no output schema, the description explains the nature of the returned data ('linking domains ranked by CrawlGraph authority') but omits details like the exact response format (e.g., list of objects with domain and score) or pagination. However, with only 5 well-documented parameters and a non-nested structure, the description is largely sufficient for an agent to call it correctly. The missing output format is a minor 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 100%—every parameter (sort, limit, domain, _apiKey, release_id) has a description in the schema. The tool description itself does not add parameter-level detail beyond what the schema provides, and with full coverage the baseline of 3 is appropriate. It mentions 'target domain' and 'linking domains' but that is consistent with the schema without extending it.

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 states a specific verb ('Returns referring domains') and resource (target domain from Common Crawl webgraph), and clearly distinguishes it from sibling tools like crawlgraph_domain_changes or crawlgraph_gap_analysis by focusing on backlink/authority data. It also names a concrete output ('linking domains ranked by CrawlGraph authority') with use cases, making the tool's purpose unmistakable.

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 explicitly lists use cases (SEO audits, competitor profiles, link-building gap research, brand citation verification) that indicate when to apply this tool. It does not name alternative tools or state exclusion conditions, but the use-case framing is enough to orient an agent. Sibling names like crawlgraph_gap_analysis imply different purposes, so the context is clear without explicit when-not guidance.

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