Asset provenance (Core)

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the behavioral burden and does so thoroughly. It discloses the bounded walk, the at-most-depth limit, the dropping of the middle of the history, the unread_gap rows placed in order, the need not to read across gaps, and the meaning of skippedTransactions. This is exactly the behavioral context an agent needs beyond the annotation hints.

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 long but densely informative and front-loaded with the core promise before moving into operational warnings. Every sentence earns its place, and the repeated warnings—read historyComplete, don't read across gaps, don't lower depth for provenance—are correctness-critical rather than fluff. The structure leads from what it does to how to interpret results safely.

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 must explain what comes back, and it does: mint, transfers with marketplace labels, current owner, historyComplete, skippedTransactions, events, and unread_gap rows. It also explains the empty-traits case and directs the agent to the right tools for traits. An agent can interpret the response safely and decide when depth is insufficient.

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 reinforces depth semantics with 'Raise depth to cover more' and warns that newer transactions are kept while the middle is dropped, but most depth details like RPC pacing, historyComplete, unread_gap, and lowering-only-for-speed already appear in the schema description. For mint, neither the schema nor the description goes beyond identifying a Core asset mint address, so the description adds only modest parameter-level value.

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 opening sentence names the exact operation and resource: 'BOUNDED on-chain ownership history of a Metaplex Core asset: mint -> transfers (with marketplace labels) -> current owner.' It further distinguishes the tool by noting it decodes from TransferV1 instruction accounts and that other APIs return empty for Core assets. Ownership-only scoping is explicit when it routes trait questions to get_asset and get_asset_trust.

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 says it is ideal for Candy Digital cards and any Core collectible, and it states what it is not for: 'Ownership events only: traits live in get_asset... and get_asset_trust.' It also gives concrete usage rules, such as always reading historyComplete before describing a trail as complete and never lowering depth to answer who-owned-it. This is strong when-to-use and when-not-to-use guidance with named alternatives.

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