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

Annotations already declare readOnlyHint and idempotentHint, but the description adds crucial behavioral nuance: it explains the distinct verdict meanings, particularly that could_not_verify means the check did not happen and carries a verification_error (not evidence against a claim), while unsupported means no source was found. It also discloses the structured path for SEC EDGAR + XBRL and the fallback grounded pipeline—information far beyond what 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 longer than average, but every sentence serves a purpose: trigger phrases, routing logic, verdict list, citation format, and the crucial could_not_verify caveat. It is front-loaded with the core trigger phrases and use case. Slightly verbose, but none of the content is filler, so it earns a 4.

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?

Given there is no output schema, the description fully compensates by explaining the return value structure (verdict, actual value with pipeworx:// citation, reasoning) and clarifying edge-case semantics. It covers routing, tolerance default, and the distinction between could_not_verify and unsupported. For a tool with this complexity, the description is remarkably complete.

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%, and the schema already fully documents both `claim` and `tolerance_pct` including examples and default behavior. The tool description mirrors the tolerance semantics ("exact percent-delta math", "capped at 5") but doesn't add new parameter meaning. Baseline 3 is appropriate because the schema carries the full load.

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 clearly identifies the tool's purpose: fact-checking natural-language claims against authoritative sources. It includes numerous trigger phrases ("Is it true that…", "fact check") and distinguishes itself from sibling tools by explaining its unique routing between SEC EDGAR structured data and a grounded pipeline. This goes well beyond a simple restatement of the name.

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?

It explicitly states "Use whenever the agent needs to check whether something a user said is factually correct" and provides detailed routing logic for company-financial claims vs. any other factual claims. While it doesn't name specific sibling tools to avoid, it offers enough context to understand when this tool is the right choice and mentions it replaces 4–6 sequential calls, helping the agent prefer it over multi-step alternatives.

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