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

Annotations declare openWorldHint=true but offer little detail, so the description carries useful additional weight. It discloses that the tool reports blocked and unreadable sources honestly and explicitly says it does not verify factual truth. This goes beyond the annotations by setting expectations for reliability and limits. It does not mention network-side effects or privacy implications, but these are reasonably implicit for a URL-checking tool.

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 short sentences, front-loads the main action and outputs, and each sentence adds meaningful information. The limitation about factual truth is valuable and not repetitive. There is no filler or unnecessary restating 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?

Given the tool's low parameter count and lack of output schema, the description covers the essential behavior, input constraints, output data points, and honest failure reporting. It could be slightly more complete by describing the result shape or matching semantics, but it is sufficient for an agent to select and invoke the tool correctly in most cases.

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 description coverage is 0%, so the description must compensate for the property definitions. It does refer to 'URLs' and 'optional quotation matches', which maps to the sources.url and sources.quote fields, and it mentions the ten-item maximum. However, it does not clarify how quotation matching works (e.g., exact, case-sensitive, substring) or how blocked/unreadable results are represented, leaving some ambiguity for an agent.

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 opens with a specific verb-resource pair: 'Check up to ten public source URLs'. It enumerates concrete outputs (successful HTTP responses, final URLs, titles, quotation matches) and adds an explicit limitation ('Does not verify factual truth'). This clearly distinguishes the tool from siblings like cleanread_read_page or tablelift_extract_tables, which serve different purposes.

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 gives clear usage context: it is for verifying public source URLs, checking their availability, and testing quotation matches. It also states the count limit (up to ten) and the honesty guarantee for blocked or unreadable sources. It does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.

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