veritas_run_pipeline

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

No annotations provided, so description carries full burden. Mentions it returns JSON with specific fields (final_verdict, gate_results, etc.), which is good. However, does not disclose potential side effects, authorization requirements, or runtime implications such as long execution time.

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?

Two concise sentences: first describes purpose and gates, second gives usage guidance and return format. No redundant or off-topic content. Front-loaded with essential information.

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 (10 gates, large claim object), description covers purpose, usage distinction, and return structure. Lacks mention of prerequisites, order guarantees, or handling of errors. Output schema is not provided, so description compensates by listing return fields.

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%, so baseline is 3. Description does not add detail beyond schema parameter descriptions; it focuses on return format. Does not clarify edge cases like partial claim objects or default behavior of fail_fast.

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?

Clearly states it runs the full 10-gate VERITAS pipeline end-to-end for evaluating a BuildClaim, listing all gate names. Differentiates from sibling gate tools by specifying 'use individual gates for targeted checks'.

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 tells when to use this tool ('complete end-to-end evaluation') and when to use alternatives ('use individual gates for targeted checks'). Provides clear decision guidance.

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