grounded_check

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

No annotations provided, so description carries full burden. It discloses being local-text only, deterministic, and lists specific excluded behaviors (source discovery, reliability scoring, factual truth). This fully informs the agent of boundaries.

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?

Four front-loaded sentences: purpose, usage, exclusions, output. Every sentence adds unique value with no redundancy or fluff.

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 one complex parameter, no annotations, and no output schema, the description fully covers inputs, outputs, and behavioral constraints. It clearly differentiates from 18+ siblings, making it complete for agent decision-making.

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 already describes the single parameter with 100% coverage, but description adds meaningful context: references a specific schema file, mentions optional verbatim quotes, and describes the return fields (grounding status, coverage, best passage, etc.), compensating for missing output schema.

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 uses a specific verb ('check') and resource ('corpus of source texts supporting claims'), clearly stating the tool's function. It distinguishes from siblings like 'verify_claims' and 'audit_claims' by specifying it checks lexical support, not factual truth.

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 when to use: when you have claims and full source texts needing a deterministic verdict before human review. Also explicitly states when not: no outbound requests, source discovery, reliability scoring, or factual verification, implying alternative tools for those cases.

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