Sentinel

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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: it screens specific list types, flags contract-vs-wallet, and returns a structured verdict with risk score, reasons, and sources. This goes beyond the annotations to clarify what the tool does and what output the agent can expect.

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 three sentences, front-loaded with the main purpose, and every sentence adds value: what it does, what it screens, and what it returns. No redundant or filler content.

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?

The tool has only 2 parameters and no output schema, so the description's inclusion of the return format (verdict, risk score, reasons, sources) is helpful. Minor gap: the description says 'crypto address' while the schema specifies 'EVM 0x…', which could cause slight ambiguity for non-EVM addresses, but overall the description is sufficient for a read-only check tool.

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%, so both parameters (chain and address) are already documented in the schema. The description does not add extra detail about the parameters themselves; it focuses on high-level behavior. Baseline 3 is appropriate given full schema coverage.

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 has a specific verb ('Check'), clear resource ('crypto address'), and a clear goal ('safe to transact with'). It distinguishes from sibling check_url by focusing on crypto addresses rather than URLs.

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 provides clear context for when to use the tool: checking crypto address safety. It mentions the screening criteria (OFAC sanctions, scam lists, contract-vs-wallet) but does not explicitly state when NOT to use it or how it compares to check_url.

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

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

Annotations declare readOnlyHint and openWorldHint, so the agent knows it's a safe read operation. The description adds value by revealing the screening sources (MetaMask blocklist, RDAP domain age, lexical flags) and return fields (verdict, risk score, reasons, sources), providing useful behavioral context beyond the annotations.

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 two sentences, front-loaded with purpose, and includes all key details without redundant wording. It efficiently conveys the tool's function, method, and output.

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?

The description fully covers what the tool does and what it returns (verdict, risk score, reasons, sources). Given the simple single-parameter schema and no output schema, this is complete and sufficient for an agent to invoke correctly.

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% with the parameter 'url' described as 'URL or domain to check'. The description adds nothing new about the parameter beyond what the schema already states, so baseline 3 is appropriate.

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 states the tool checks if a URL or domain is a scam/phishing site, specifying the verb 'Check' and the resource 'URL or domain'. It also distinguishes itself from the sibling 'check_address' by focusing on URLs/domains rather than addresses.

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 implies usage for URL/domain safety checks but does not explicitly mention alternatives or when not to use it. With a sibling tool 'check_address', the lack of explicit differentiation or usage guidance is a minor gap, though context is clear.

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