preview_sandbox_match

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

With no annotations provided, the description fully discloses behavioral traits: auth requirements (X-API-KEY header, AIDRESS_API_KEY), error condition (403 if no live counterpart), comparison logic (draft's own config but live stats), competitor filtering (verified=true, trust_score>=50, live counterpart excluded), and side-effect-free execution. It even notes the explanation is null if LLM call fails and never blocks results.

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 structured in clear paragraphs: purpose, auth, parameter details, behavioral details, return values. Every sentence adds necessary context; there is no fluff, despite the length.

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?

For a complex preview tool with no output schema, the description covers inputs, outputs (ranked results, draft_agent_id, explanation or null, disclaimer), error conditions, and side effects. It is complete enough for an agent to invoke correctly.

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 has no descriptions (0% coverage), but the description explains all three parameters: sandbox_agent_id (prerequisite/403), required_capabilities (same semantics as match_agents), and settlement_rail (enum values and omission behavior). This fully compensates for the empty 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 opens with 'Preview exactly where a sandbox agent's tested config would rank against REAL, live competition — before you actually promote it,' providing a specific verb (preview), resource (sandbox agent config vs live competition), and purpose (pre-promotion evaluation). It distinguishes itself from sibling tools like promote_sandbox_agent and match_agents by framing the comparison and non-mutating nature.

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?

It explicitly states the context 'before you actually promote it' and defines prerequisites (sandbox_api_key, sandbox_agent_id must have live counterpart). It references register_agent's clone_from_agent_id and match_agents semantics, and clarifies 'Nothing here is written anywhere', telling the agent when this preview tool is appropriate vs actual promotion.

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