Market Signal Fabrication Screen

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

With annotations all false, the description carries the full burden and does so admirably. It discloses cost ($0.03), reliance on output text alone (no price feed), the specific heuristic patterns, false-positive potential, non-authoritative status, and the verdict/confidence collapsing rule referencing dcl_evaluate_mev. This goes well beyond 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?

Though lengthy, every sentence is purposeful: it opens with the tool's name and cost, details the heuristic flags, provides a limitation/caveat, offers an alternative, and explains the verdict rule. It is front-loaded and well-organized, no 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?

The description covers the tool's purpose, behavior, limitations, alternatives, and verdict logic. An output schema exists to handle return structures. It even cross-references a sibling tool for the collapsing rule, providing comprehensive context for an AI agent to correctly select and invoke the 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 input schema already provides 100% parameter descriptions (agent_id, response, payment_id), so the baseline is 3. The description adds some context about payment ($0.03) and POST-ACTION orientation, but does not significantly enhance parameter-level meaning beyond what the schema already states.

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 a specific verb+resource: 'Market Signal Fabrication Screen' with a precise pattern-based heuristic that flags guaranteed-price-prediction language, absolute-certainty claims, fabricated-price flags, and invented-token flags. It distinguishes itself from sibling evaluators by name and by referencing the local grounding workflow and dcl_evaluate_mev.

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 explicitly states when not to use it ('For a full claim-by-claim check against an actual price-feed snapshot, use the local grounding workflow instead of this live tool') and labels it as a 'heuristic pre-check, not ground truth.' It implies when to use (POST-ACTION, quick screen) but does not enumerate all positive use cases.

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