provider_reliability_verdict

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

Beyond annotations (readOnly, not destructive), the description discloses the scoring method (availability and tail consistency equally), rate limits (10 calls/day/IP for preview), authentication needs (TENSORFEED_TOKEN for full), and the signed receipt feature (AFTA). No contradictions with 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?

The description is packed with essential information in a few sentences: purpose, scoring, tier options, pricing, limits, and token link. Every sentence adds value; no fluff. It is front-loaded with the main purpose.

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 the complexity (scoring, tiers, signed receipts, limits) and absence of output schema, the description adequately explains what the tool returns for each tier, the authentication and payment details, and the reasoning behind the scoring. No obvious gaps remain.

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?

The single parameter 'tier' is fully described in both schema (enum, description) and the tool description, which adds context about pricing, rate limits, and output differences. Schema coverage is 100%, so baseline is 3; the description adds marginal value, justifying a 4.

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 states it provides a 'signed dependability ruling' on AI providers, naming the specific output: 'the single most-dependable provider to build on and the riskiest'. It distinguishes from siblings by focusing on provider reliability and mentioning unique features like scoring and signed receipts.

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?

The description explains when to use each tier ('preview' free vs 'full' paid), including rate limits and token requirements. However, it does not explicitly compare to sibling tools (e.g., failover_verdict, benchmark_trust_verdict) or state when not to use this tool.

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