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

The description reveals one behavioral trait — the title is discarded after the call — but annotations are absent, so the description should carry more burden. It does not disclose return shape, network access, error behavior, or whether any other input fields are used.

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 one short sentence with no filler and front-loads the core action. It is economical, though it omits essential operational detail.

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 tool with no output schema and an eight-parameter schema that does not obviously match the purpose, the description is drastically incomplete. An agent cannot correctly invoke it without guessing which parameter carries the Wikipedia title.

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 documents all eight parameters, but their meanings are unrelated to the described purpose (e.g., ref is a Git ref, city is a weather hint, feed is an RSS URL). The description adds no mapping from any parameter to the Wikipedia title, so a caller cannot determine which field should hold the title.

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 operation — check whether a Wikipedia title exists — which distinguishes it from sibling OK/shape tools. However, the input schema has no 'title' parameter, so the stated purpose is not clearly connected to any actual input, which slightly undermines clarity.

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 guidance about when to use this tool vs alternatives such as normalize-url, validate-json, or other *-ok checks. The description gives no conditions, prerequisites, or exclusions for invoking this tool.

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