token_dossier

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

With no annotations, the description carries the full burden and does so: it discloses payment mechanics (PAID x402, USDC on Base, MCP server needs a funded wallet to settle), a fixed price, no free trial, the POST body shape, and the failure semantics — each section reports its own status and limits[] enumerates what could not be established, with the reason stated ('a silently missing section reads as reassurance'). It also states a non-obvious result rule: the verdict is inherited and may only be escalated, never softened.

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?

Front-loaded with the payload inventory before the caveats and pricing, and most sentences carry real information (status/limits semantics, verdict escalation rule). A few phrases are promotional padding ('what distinguish a bad token from a serial rugger', 'No free trial on this stall') that could be trimmed without loss.

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?

There is no output schema, so the description must describe return values — and it does, section by section, including the archive's per-removal fields (amount/block/tx) and the operator-linkage signal. Combined with the payment and limits[] disclosure, an agent has everything needed to decide, invoke, and interpret the result.

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 both parameters (token, chain) are already documented in structured form; the description only restates the required token via 'POST `{ token }`'. It says nothing about the chain parameter or its base-only constraint beyond the framing. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Opens with a specific verb-and-resource framing ('Everything we know about a Base ERC-20, in one call') and then enumerates the exact contents: conformance, ownership, mint-capability, honeypot simulation, rug/whale activity, verdict, deployer reputation, and the durable liquidity archive. It explicitly contrasts itself with 'the cheaper report' (token_report), so an agent can separate it from token_safety/token_report without opening a schema.

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?

Usage context is clear — this is the escalation path when the two extra sections (deployer reputation, operator-linked liquidity removals) matter, i.e. 'what distinguish a bad token from a serial rugger'. It names the cheaper alternative implicitly rather than by tool name and gives no explicit 'do not use this for X' exclusion, so it stops short of a 5.

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