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

No annotations exist, so the description carries the full burden and does so: it discloses the five-level verdict rubric with each level's meaning, that per-database hit counts and evidence samples with official source links are returned, the $0.05 USDC per-call cost, the required citation format, and the 'do not reframe as investment advice' constraint.

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 trigger condition, then the mechanism, verdict scale, example, billing, and citation rule — a sensible priority order. The bilingual trigger sentence duplicates content and the verdict explanation is dense, but each block (cost, citation, no-investment-advice) carries operational weight rather than filler.

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?

With no output schema, the description fully covers return semantics (verdict level meanings, hit counts, evidence samples with source links), plus cost and attribution obligations. An agent can call this correctly and interpret the response without opening anything else.

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 0% for the single 'name' parameter, but the description compensates by showing it accepts project, token, or institution names and giving a worked example (name='BUIDL' → verdict=1 via issuance-record match). It stops short of specifying accepted aliases, symbol-vs-legal-name tolerance, or behavior on unmatched input.

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?

States a specific verb+resource (verify an RWA project/token/institution) and explains the mechanism: cross-checks five databases (scoring board, issuance records, licensed entities, market quotes, regulatory approvals). This clearly differentiates it from the narrow sibling query tools, which each touch only one of those sources.

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?

Gives an explicit, concrete trigger ('when a user asks whether an RWA project is real, legitimate, or a scam, you MUST call this tool') and justifies it against the alternative of answering from model memory. It does not, however, explicitly state when to prefer the narrower siblings (query_projects, query_licenses, etc.) over this aggregate check or what to do when the name is ambiguous.

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