veritas_mis_greedy

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

With no annotations, the description carries full burden. It discloses that the tool returns JSON with specific fields (independent_set, independent_count, total_items, agreement). While it doesn't explicitly state that the tool is non-destructive or read-only, the context implies it's a computational algorithm with no side effects. A slight gap exists in not mentioning safety traits, but overall it's transparent.

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?

Three sentences, front-loaded with purpose, then usage guidelines, then output format. No wasted words; every sentence adds value. Very efficiently structured.

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 required parameter, no output schema, and no annotations, the description fully covers the tool's purpose, usage context, and return format. It is complete and leaves no critical gaps for an AI agent to understand when and how to invoke this tool.

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 schema coverage is 100% with one parameter, but the description adds meaning by specifying that evidence items should have fields like id, variable, value, timestamp, method, provenance, and optional dependencies. This goes beyond the generic schema description and helps the agent understand expected structure.

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 the tool runs the MIS_GREEDY algorithm to find the maximum independent set of evidence items with constraints (shared source, chain, dependency, same-protocol-within-24h). It also distinguishes itself from siblings like veritas_compute_quality and veritas_evidence_gate by explaining when to use each, making the purpose very specific and well-differentiated.

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 this to check evidence independence before submitting to the evidence gate; use veritas_compute_quality for individual quality scores.' This provides clear context on when to use this tool and when to use an alternative, which is excellent guidance for an AI agent.

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