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

With no annotations, the description carries the full load and does so richly: it defines 'unknown' as incomplete coverage rather than 'checked clean', explains the freeze-history backfill behavior that downgrades a would-be 'none' to 'unknown', scopes freeze to this chain alone, and states 'No auth' plus 'Not an identity/AML/legal determination'. This is exactly the behavioral context an agent cannot get from structured fields.

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 core verdict statement, then progressively qualifies scope, exclusions, and semantics. Sentences are dense and parenthetical-heavy, but nearly every clause carries distinct meaning; a slightly lighter touch could have trimmed the parentheticals 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?

For a tool with no output schema and no annotations, the description must convey the return shape and safety profile, and it does: tier values, the meaning of 'unknown', the single-chain scope, and lack of auth. The multi-chain re-query flow is described but the returned envelope fields (chain_id, chain_source) are only referenced, not fully explained in the description text.

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 description coverage is 100% and the schema itself is extremely detailed about chain spellings, defaults, and chain_id/chain_source. The description adds no parameter-level syntax beyond what the schema already provides, so the baseline of 3 applies.

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 resource and output: a single unified risk tier (unknown|none|low|medium|high|severe) for an address, with the exact inputs it aggregates (decoded facts vs attributed labels). It distinguishes itself from get_address_compliance by naming what it deliberately does NOT score. An agent can tell it apart from siblings 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?

Explicitly routes the freeze-elsewhere/proposal questions to get_address_compliance, and warns that a lone-source label contributes no tier. It also explains that a chain answer covers ONE chain and that the caller should read chains_with_data and re-ask with chain set. No guidance against the other siblings (exposure, sanctions_status, approvals), so not a full 5.

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