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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavior beyond them: auth tiers and the paid-plan gate on 'thorough', latency expectations (15-60s, up to ~90s), the never-invents guarantee via gaps[], the resolvable-citation guarantee, contradictions[] behavior per depth, semantic excerpting of large records, and the hop field. No statement contradicts the annotations.

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?

Every sentence earns its place — there is no filler and the front-loading is good (auth gate first, then routing to the alternative). However, the entire definition is one dense, unbroken paragraph with heavy parentheticals and semicolons, making parsing harder than necessary. Structure is the clear weakness despite excellent information density.

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 high-complexity tool with no output schema, the description must carry the return-format burden — and it does thoroughly: findings packet structure (verbatim evidence + confidence + source + fetched_at + citation), gaps[] and contradictions[] semantics, citation fetchability, hop field, excerpting behavior, auth requirements, latency, and sibling routing. Nothing required for correct invocation is missing.

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's depth description is already very rich, so baseline is 3. The description adds meaningful extra semantics: latency expectations tied to depth, the 'multi-step questions resolve in one call' rationale for the iterative hops, and concrete question-phrasing examples for the question parameter ('compare X and Y's regulatory + financial exposure'). This exceeds what the schema alone provides.

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 Pipeworx's 1506 STRUCTURED data sources... in ONE call', and immediately distinguishes itself with 'this is NOT open-web search'. It also names sibling ask_pipeworx as the alternative for single lookups and current news, making the tool's identity and scope unmistakable.

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?

Provides explicit when-to-use guidance ('Best for broad/multi-part questions over structured data') and explicit when-not-to-use exclusions ('For a single lookup use ask_pipeworx instead', 'For BREAKING or colloquial current-news... prefer ask_pipeworx'). It even covers the auth edge case: 'If you are not signed in, use ask_pipeworx instead'. Alternatives are named precisely.

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