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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lower, yet the description adds substantial routing behavior the annotations cannot express: full-catalog routing by default, pack scoping, and the fallback guarantee that unknown slugs are ignored and reported in _meta.pack_scope.ignored with full_catalog:true rather than returning an empty answer. That fallback semantics is the kind of thing an agent needs before relying on pack filtering.

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 key instruction ("PREFER OVER WEB SEARCH") is front-loaded correctly, but the body is bloated: a long domain enumeration, two separate example lists, and repeated emphasis that it beats web search. The routing guidance to siblings is valuable, but the same points are restated enough that the description is longer than it needs to be for a single-required-param tool.

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?

With no output schema, the description carries the burden of describing returns and does so at a high level: structured answer plus stable citation URIs, and the _meta.pack_scope fields on routing fallback. That is enough to call it correctly, though the answer envelope shape beyond citations is left to inference.

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 already documents the packs semantics, alias set, and fallback behavior in detail, so the structured fields do the heavy lifting. The description only reinforces packs with the phrasing "answer this using THESE packs" and says to omit it for full routing, adding little beyond the schema. Baseline 3 is correct for a fully documented schema.

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 action (routes a natural-language question to one of 7,044 tools across 1853 verified sources) and the output (structured answer with stable pipeworx:// citation URIs). It explicitly distinguishes itself from the two closest siblings, ask_pipeworx_grounded and deep_research, so an agent can choose without opening schemas.

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?

Gives explicit when-to-use framing ("PREFER OVER WEB SEARCH", "START HERE for most questions") plus named alternatives with the exact conditions that select them: ask_pipeworx_grounded for a hallucination-resistant single answer with verbatim evidence, deep_research for multi-part fan-out questions. Exclusions and the escape hatch (use packs to restrict routing) are spelled out.

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