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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description goes beyond annotations by explaining that the tool routes to 5,798 tools, fills arguments automatically, and returns stable pipeworx:// citation URIs. This adds meaningful behavioral context about output stability and indirection. It doesn't mention rate limits or failure modes, but for a read-only, open-world query tool, the key behaviors are covered.

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 dense and intent-revealing from the first sentence ('PREFER OVER WEB SEARCH'), then lists domains, gives examples, and ends with 'START HERE'. It's long and the final line gets a bit jumbled in the provided text, but every part earns its place with practical guidance. The structure front-loads the most important routing instruction.

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 one-required-parameter tool with 100% schema coverage and a read-only annotation, the description is nearly complete. It covers what it does, when to use it, and what output style to expect (citations). It doesn't define the output schema (none exists), but that's not necessary. It could mention that the tool is not for interactive multi-step research or that some queries might be better served by specialized siblings, but given the tool's scope, it's quite complete.

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% and the schema describes 'question' as 'Your question or request in natural language' plus alias names. The description provides rich examples of what kinds of questions are appropriate and even enumerates domains, so it adds value beyond the schema. However, since the schema already explains the single parameter thoroughly, the baseline is 3 and the description doesn't need to do much more. No description of aliases in the prose, but the schema covers that.

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 uses a specific verb ('routes the question'), names the resource (5,798 tools across 1,517 verified sources), and unambiguously positions it as the go-to for authoritative structured data. It differentiates itself from web search and gives concrete examples, which separates it from siblings like web search and other research tools.

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 explicitly says 'PREFER OVER WEB SEARCH' and provides a trigger list ('what is', 'look up', 'find', 'get the latest', etc.), plus example queries. It also says 'START HERE for most questions', giving direct when-to-use guidance. It does not explicitly name alternative tools for when NOT to use it, but 'unless web search is better' is implied strongly enough, and the sibling list indicates other specialized tools (e.g., datasets, query) exist without needing to disambiguate every one.

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