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

Beyond the readOnly/openWorld annotations, the description discloses response semantics that are not obvious: per-window last_buy_at/last_sell_at fields, a shared data_as_of rollup boundary, and a specific interpretation trap (a net that flips without a newer last_sell_at means aged-out buys, not new selling). That is exactly the kind of behavioral context annotations cannot carry.

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 lead sentence is front-loaded with the actual question the tool answers, and the window/data_as_of caveat earns its space. However, the 'never the user's wallets' point is made twice in near-identical wording, which is redundant for a description of this length.

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 two-parameter read-only tool with annotations covering safety and an output schema covering return shape, the description supplies everything else an agent needs: what the signal means, the time-window structure, and the main misreading to avoid. Nothing material 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 description coverage is 0% across two parameters, so the description must compensate and largely doesn't. 'This token' weakly implies token_address, but the network parameter (const 'solana', defaulted) is never mentioned, nor is the expected address format for token_address.

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 resource (tracked high-performing wallets positioned in a token) and the dimension returned (which side they're on), with a concrete framing question ('is anyone good in this?'). It cleanly separates itself from the get_my_* family, but does not differentiate against close token-holder siblings like get_token_whale_holders, get_token_key_holders, or get_top_held, so an agent could still hesitate between them.

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?

It gives clear usage context ('Moby's core edge signal') and an explicit exclusion plus alternative: it is not the user's own data, and tools prefixed get_my_ return that. There is no guidance on when to prefer this over the other token-holder/whale-holder tools, which is the more likely sibling confusion.

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