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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the description doesn't need to repeat that. It adds useful behavioral context by specifying the tool returns 'counts plus a bounded list of associated URL and payload observations,' which informs the agent that the output is not an unbounded set and that both counts and observations are included. This goes beyond annotations but still leaves minor details like pagination or default not mentioned, though the limit parameter covers that.

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 a single sentence, around 15 words, that captures the main action (lookup), the resource (signature), and output characteristics (counts plus bounded observations). It is front-loaded and contains no redundant filler or repeating the title. Every word 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 small, focused tool with two parameters and a read-only/ anonymous annotations, the description covers enough for an agent to correctly invoke it. It states what is looked up and what is returned. It does not list return field names (no matter output schema is given), but the core behavior is well covered. The main gap is that it does not explicitly steer to sibling tools for other search keys, but the description is still complete enough given the tool's simplicity.

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 itself describes both parameters: 'signature' as a malware-family signature with safe characters and limit as maximum records (default 20, max 50). Since schema description coverage is 100%, the description doesn't need to add much. It adds slight contextual reinforcement, such as saying 'signature' for URLhaus, but does not meaningfully go beyond what the schema already provides.

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 starts with a specific verb and resource: 'Look up a URLhaus malware-family signature' and explicitly states the tool returns 'counts plus a bounded list of associated URL and payload observations.' This clearly distinguishes it from sibling tools like urlhaus_lookup_host, urlhaus_lookup_url, and urlhaus_lookup_payload, which focus on other identifiers. There's no tautology; the description fully describes the tool's function.

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 makes it clear that this tool is for signatures, so when an agent holds a malware-family signature it is obvious to use this tool. However, it does not explicitly mention sibling alternatives (e.g., 'for host-based lookups use urlhaus_lookup_host') or state when not to use it. The context implies usage but does not provide there are exclusions or alternate path guidance.

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