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

The description discloses rich behavioral traits beyond the readOnlyHint annotation: the tool does NOT report listings/offers/mints/transfers, so an empty result must not be interpreted as 'none of those occurred'; results are sorted most recent first; not every row is a sale; PREMIUM_REGISTRATION is a Dutch-auction registration not a secondary-market sale and has no price; SWAP is a name-for-name trade with no price; SALE includes accepted offers; and the tool makes no wash-trading judgment. This is exceptional behavioral transparency that prevents critical misuse.

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 dense but every sentence earns its place — each adds either scope clarification, interpretation guidance, or a misuse warning. The most critical constraint (exactly three event types) is front-loaded, and the trafficking warnings about PREMIUM_REGISTRATION and SWAP are placed near the relevant context rather than buried. The length is justified by the number of distinct behavioral facts an agent must know to avoid errors.

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 read-only filtered list tool with 3 self-describing parameters (100% schema coverage), the description covers everything needed: scope, exclusion semantics, event-type interpretation, sort order, return fields, and the sibling tool for a different question (wash_check). The absence of an output schema is compensated by the description's explicit enumeration of returned fields. Nothing an agent needs to call or interpret this tool correctly is missing.

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 the baseline is 3; the description adds meaningful value above that baseline. It explains what each event type means semantically (crucially that PREMIUM_REGISTRATION is not a sale and SWAP has no price), which the schema's bare enum names do not convey. The description also mentions the returned fields include name, price in ETH, buyer/seller addresses, and timestamp, helping an agent understand what 'limit' and 'offset' paginate. Only minor gap: it doesn't explicitly restate parameter defaults beyond the schema, but the schema already has that.

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 states a specific verb ('Get'), resource ('ENS marketplace activity'), and explicit scope: exactly three event types — SALE, PREMIUM_REGISTRATION, and SWAP. It goes further and explicitly names what is NOT covered (listings, standing offers, mints, transfers, renewals, burns), which crisp distinguishes it from siblings like get_expiring_names, get_name_details, and wash_check. The level of precision leaves no ambiguity about the tool's function.

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 tells the agent when to use this tool versus alternatives: for wash-trading/fake-volume questions, it directs to 'use wash_check'. It also conveys when NOT to use results as evidence (e.g., PREMIUM_REGISTRATION should not be quoted as secondary-market sale evidence). It explains the semantic context needed to correctly interpret results — check the 'type' field before describing a row as a sale. This is the gold standard for usage guidance.

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