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

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and safe=true, so the description does not need to repeat the safety profile. It adds one behavioral detail, 'Title discarded after the call', which addresses data retention. It does not describe the existence-check mechanism or output format, but for a read-only checker this is adequate.

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 only two short sentences with the core action front-loaded and no fluff. However, the second sentence is confusing because there is no title parameter in the schema, and the brevity leaves critical invocation details unstated, making it under-specified rather than cleanly concise.

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 output schema and seven schema properties, the description should clarify which parameter represents the title and what the return contract is. It provides neither, and the mismatch between the stated purpose and the parameter list makes the tool effectively non-invocable without further investigation, despite the safety annotations covering side effects.

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 schema has seven parameters, all with individual descriptions, so schema description coverage is high. Yet the description's key noun 'title' does not appear in the schema, and no property is identified as the Wikipedia title; ref, url, city, feed, host, json, and path are described as unrelated values. The description fails to help an agent select the correct argument, which is the core invocation problem.

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 action ('Check whether a Wikipedia title exists') and a clear resource, making the tool's purpose identifiable and distinct from most shape-checker siblings. However, it never connects the stated purpose to any input parameter, so the purpose is not fully actionable from the description alone.

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?

There is no when-to-use or when-not-to-use guidance, and no mention of alternatives such as domain-shape, browser-url-ok, or normalize-url. The only implication is that this tool performs a validation check, but no routing criteria or exclusions are provided.

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