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

Annotations declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds critical behavioral context beyond that: it warns that could_not_verify means the check did not happen and 'must not be shown as one' (i.e., as evidence), and explains unsupported as a coverage limitation. It also discloses the underlying pipeline (NL parsing → entity resolution → data lookup → comparison), which is far more than annotations provide.

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 fairly long but every sentence serves a purpose: examples, routing, return payload, error semantics, and pipeline replacement. It is front-loaded with the most important information (what it does) before going into details. One minor redundancy: 'Replaces 4–6 sequential calls' could be omitted without losing core meaning, but it still adds value by framing efficiency.

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: verdict types, actual value with citation, reasoning, and error semantics. It also covers the two distinct categories of claims (financial vs. other) and how they are routed. For a tool with 2 params, multiple verdicts, and error states, this description is complete enough for an agent to select and invoke it 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 description coverage is 100%, so the baseline is 3. The description mentions 'exact percent-delta math' and 'capped at 5' which relates to tolerance_pct, but the schema already explains tolerance_pct and its default in detail. The description adds no new parameter-level meaning beyond what the schema provides, so a 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?

The description opens with concrete natural-language triggers and states a specific verb+resource: 'natural-language claim verification against authoritative sources.' It clearly distinguishes from sibling tools like search or ask_pipeworx by framing the tool as a fact-checker that returns a verdict, not just information. The 'Replaces 4–6 sequential calls' line further positions its unique purpose.

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?

Explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct,' which is clear when-to-use guidance. It also explains the two routing paths (SEC EDGAR for company financials, grounded pipeline for anything else), giving the agent a decision procedure. The distinction between could_not_verify and unsupported gives important usage guardrails.

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