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

Goes well beyond the readOnly/idempotent annotations: names expected latency (15–60s, ~90s for thorough), discloses that gaps[] are never invented, that standard/thorough return contradictions[], that large records are semantically excerpted rather than head-truncated, and that citation_uri is only present when resources/read can actually serve it. That last point is a genuinely non-obvious caveat an agent could otherwise misread.

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?

Front-loaded with the account prerequisite, which is the highest-stakes fact, then purpose, then routing rules, then return shape. Dense but nearly every sentence carries new information; only the alias enumeration and the depth restatement overlap with the schema.

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?

There is no output schema, yet the description still specifies the return shape (findings packet, evidence + confidence + source + fetched_at + citation_uri, gaps[], contradictions[], hop field), which is exactly the burden it must carry. The only minor gap is that multi-hop cost/latency for standard vs. quick is given as a range rather than per-tier.

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 depth enum is fully documented in the schema itself, so the description's restatement of quick/standard/thorough largely duplicates structured data. The one piece of added value is framing depth as a second-hop iteration mechanism (gap recovery vs. lead-chasing), but that is already largely present in the schema description — baseline 3 is appropriate.

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 (grounded multi-source research across 1,851 structured sources in a single call) and immediately bounds it with 'this is NOT open-web search'. It also explicitly distinguishes itself from the nearest sibling, ask_pipeworx (one LLM call, single lookup), so an agent can route without opening either schema.

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 positive conditions (broad/multi-part questions over structured data, with two concrete example phrasings) and explicit negative routing (single lookup → ask_pipeworx; breaking or colloquial current-news → ask_pipeworx, with the reason: mostly empty gaps[]). It also surfaces a prerequisite an agent cannot get from the schema: an account is required, free via GitHub, and depth:'thorough' needs a paid plan.

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