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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely non-obvious behavior — account and paid-plan gating, 15–60s (up to ~90s) latency, never-invented gaps[], contradiction scanning, semantic excerpting of long records instead of head truncation, and a guarantee that returned citation_uri values are actually resolvable via resources/read. The only gap is that it doesn't describe result size or how many findings to expect.

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-loads the highest-stakes facts (account requirement, fallback to ask_pipeworx) before the capability pitch, which is the right ordering. However, it is a single dense paragraph of roughly 300 words with heavy parenthetical nesting and some redundancy between the description and the depth enum, making it harder to scan than it needs to be.

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 full burden of explaining the return value, and it does: a findings packet with verbatim evidence, confidence, source, fetched_at, pipeworx:// citation per finding, gaps[], contradictions[], and a hop field. Combined with auth, cost, and latency disclosure, an agent has everything needed to decide and call correctly.

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 depth and question are already documented in detail; the description adds meaning the schema lacks — that depth:'thorough' requires a paid plan, and how the depth tiers relate to hops ('standard' re-angles gaps, 'thorough' chases leads). The alias set is restated rather than clarified, which keeps it below a 5.

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 1947 STRUCTURED data sources in ONE call') and explicitly negates a plausible misreading ('this is NOT open-web search'). It also contrasts with the closest sibling, ask_pipeworx, so an agent can separate the two 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 routing rules: signed-out users go to ask_pipeworx, single lookups go to ask_pipeworx, breaking/colloquial news should prefer ask_pipeworx because deep_research returns empty gaps[]. It even explains the failure mode ('returns mostly empty gaps[] when the topic isn't in the structured catalog') that should drive the alternative choice.

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