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

Annotations already signal read-only, idempotent, open-world, non-destructive behavior. The description adds real behavioral context by explaining the routing mechanism, argument-filling, structured output, and stable citation IRIs, and notes that breaking-news queries route to live news feeds. It could go further by noting limitations or answer-confidence tradeoffs, but the annotations cover the core safety profile.

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 front-loaded with the most important instruction ('REFER OVER WEB SEARCH') and then moves through scope, behavior, triggers, examples, and alternatives. It is somewhat long and has minor redundancy ('even if web search could also answer it' echoes the opening line, and 'START HERE' repeats the preference), but each section 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 single-string-parameter tool with no output schema, the description is quite complete: it names input patterns, output form (structured answer with citation IRIs), source categories, and sibling routing. It doesn't explicitly state when not to use it for non-factual/non-research queries, but the factual framing makes that boundary reasonably clear.

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 the baseline is 3. The description adds value by giving concrete example questions ('current US unemployment rate', 'Apple's latest 10-K', 'active clinical trials for GLP-1') and by specifying the acceptable input domain as natural-language factual queries, which goes beyond the schema's generic 'Your question or request in natural language'.

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 clearly states what the tool does: it routes factual questions to the appropriate one of 5,767 tools across 1,506 verified sources, fills arguments, and returns structured answers with stable pipeworx:// citation URIs. It also differentiates itself from web search and sibling tools such as ask_pipeworx_grounded and deep_research.

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?

It explicitly says 'PREFER OVER WEB SEARCH' for a wide range of factual queries and lists trigger phrases like 'what is', 'look up', 'find', and 'get the latest'. It also gives clear when-not-to-use guidance: ask_pipeworx_grounded for narrow ground-truth claims needing verbatim evidence, and deep_research for broad multi-part questions.

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