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

The description adds an important behavioral disclosure not captured by the annotations: it does not contact the reported URL during the lookup. Combined with the readOnlyHint and idempotentHint, this is transparent about the non-interactive, read-only nature of the call, going beyond what structured annotations alone provide.

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 with no filler, leading with the action verb and target, then listing the key returns and safety behavior. Every component—resource type, accepted inputs, return types, and the explicit 'without contacting the reported URL' caveat—earns its place.

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 lookup tool with 100% schema coverage, zero required parameters, no output schema, and strong annotations, the description provides enough context: what inputs to pass, what data comes back, and its non-contact safety behavior. It does not discuss pagination or response formats, but those are not critical for correct invocation at this complexity level.

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?

Although the schema already covers the parameters, the description adds semantic meaning by clarifying that the tool accepts exactly one URL or one numeric record ID. This implies mutual exclusivity between url and url_id, which the schema alone does not state, and also reinforces that the input is a single indicator rather than a host or payload.

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 ('threat intelligence for exactly one HTTP(S) or numeric URLhaus record ID'), which is specific enough to distinguish it from sibling tools that search by host, payload, tag, or signature. The mention of exact input types and return fields makes the tool's purpose unambiguous.

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 context for when the tool applies: a single HTTP(S) URL or numeric URLhaus record ID, not bulk or list-style lookup. However, it does not explicitly mention alternatives like urlhaus_lookup_host or urlhaus_lookup_payload, nor state when to avoid this tool, so it falls short of full when/when-not guidance.

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