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

Annotations already declare readOnly/openWorld=false safety, so the bar is lower; the description still adds value by disclosing the two-phase search-then-read flow and the shape of results (matching pages, matched lines, links). It stops short of describing ranking, result limits, or what an empty/no-match response looks like.

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 sentences, zero waste, and the use-case trigger is front-loaded ahead of the mechanics. Each clause earns its place.

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 two-param read-only retrieval tool with no output schema, it supplies the trigger conditions, the return content, and the follow-up pattern. An agent has everything needed to decide when to call it and how to continue from the result.

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 coverage is 100%, so both parameters are already documented. The description adds the workflow relationship between them — `page` is used on a second call to read in full, `question` is for the initial search — which clarifies sequencing beyond the standalone field text.

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 verb and resource ('Searches the WebTwizz docs') plus the return content ('best matching pages with the lines that match and links'). This is clearly distinct from the site-management siblings, which cannot be confused with a docs lookup.

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?

Opens with an explicit trigger set: 'when the user asks how to do something in WebTwizz, how a feature works, or about plans and limits.' It also names the follow-up pattern ('call it again with a page title to read one in full'), so both invocation modes are routed.

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