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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description's burden is lower. It still adds real behavioral context: the quantified blind spot (~69% coverage via the 14k-domain Citizen Lab list), the framing that the tool exposes its own limitation, and the exact return contents.

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 question, then the return shape, then the use case — every clause carries information. The em-dash aside about disclosing a blind spot is editorial but still informative; a slightly tighter phrasing would reach 5.

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?

With no input parameters and no output schema, the description carries the full burden and discharges it by naming the aggregate and per-category return values plus the coverage figure. Nothing an agent needs to call this correctly or interpret the result 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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no input configuration is needed and focuses entirely on what the call produces.

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?

States a specific measure (what fraction of the measured-domain corpus carries a Citizen Lab category) plus the concrete output shape (tagged/untagged counts and per-category domain counts). This is clearly distinct from siblings like get_categories or get_censorship_by_category, which return category data rather than coverage-of-categorization meta-data.

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?

"Use to gauge how complete any 'by category' analysis is" gives a clear triggering condition and implicitly routes the agent here before trusting category breakdowns. It stops short of naming the specific sibling tools whose results it qualifies, so it is not a full when/when-not/alternatives statement.

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