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

Annotations already mark readOnlyHint and destructiveHint, so the description adds value by warning that the tool only answers read-shaped calls and refuses buy/sell/write operations, and by explaining how to interpret an empty list. The external 'their data comes back as it is' caveat is also useful, though the prose is muddled.

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 core sentence is front-loaded and specific, but the rest is poorly structured: the second sentence is a fragment with an em-dash splice, followed by vague claims about being called through a seat and a URL. Useful details are present but not organized concisely.

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 zero-parameter read-only tool without an output schema, the description covers the key interpretation guidance (completeness, empty list meaning) and read-only behavior. However, 'unconfigured index' and 'called through their seat' are left undefined, and the description does not explain how an agent would specify the address and chain if needed.

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?

The schema declares no required parameters and has no documented properties, so the baseline is 4. The description does not document parameter names, but it mentions the conceptual inputs (address, one chain), which is sufficient for a zero-parameter tool.

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 clearly identifies the resource (recent transactions for an address on a single chain) and ordering (newest first). It does not use an explicit verb like 'list' or 'get', and it does not name sibling tools such as singularityagent__transaction, leaving minor ambiguity about why this is the history tool versus a singular transaction lookup.

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 gives clear usage context: read the completeness field before the entries and be aware that an empty list may mean no activity or an unconfigured index. It also says the tool is read-only and refuses writes, but it does not explicitly name alternative tools or exclusion conditions.

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