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

With no annotations, the description carries the burden. It does disclose that the tool returns host/scheme/HTTP status and that page content is not stored, which is useful privacy/behavioral context. However, it omits auth needs, error behavior, whether a network request is made, and rate-limit implications.

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?

Two short sentences, front-loaded with the primary purpose and a concise data-handling note. No fluff, but the brevity undersells the tool's nine-parameter surface and sibling distinctions.

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 nine optional params, no annotations, and no output schema, the description is not complete. It fails to explain how params like city, feed, json, path, zone, and query relate to the tool, and it does not distinguish this from closely named siblings.

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 input schema has 100% description coverage, so the baseline applies; description adds no parameter detail. It only reinforces that the main input is a URL, while the other eight params are unmentioned in the description.

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 and output: 'Return host, scheme, and HTTP status for a URL.' It is clear on its face, but the tool name 'citation' is not reflected, and it does not distinguish itself from siblings like fetch-status or normalize-url.

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 guidance, alternative comparison, or prerequisite. The phrase 'Page content is not stored' is a behavioral note, not a routing rule, so an agent cannot tell whether to choose this over web-fetch, fetch-status, or normalize-url.

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