contrastapi

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

With no annotations provided, the description carries full behavioral disclosure burden yet states nothing about safety (read-only vs destructive), rate limits, authentication requirements, or return format. 'Scan' implies activity but lacks transparency on impact.

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?

While brief, this represents under-specification rather than efficient conciseness. The single sentence contains no actionable information, though it avoids unnecessary verbosity.

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?

Despite having only one parameter, the complete lack of schema documentation and absence of output schema means the description should provide substantial context. It provides none, leaving the tool's function and requirements entirely undefined.

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% (domain parameter has empty description), and the main description fails to compensate by explaining what 'domain' expects (format, example) or its role in the operation. No parameter semantics are conveyed.

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 'Scan Headers Endpoint' is tautological, merely restating the tool name with 'Endpoint' added. It fails to specify what 'scanning' entails (security analysis? retrieval?) or distinguish from sibling tool 'check_headers'.

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?

No guidance provided on when to use this versus the similar 'check_headers' tool, or prerequisites like domain ownership verification. Zero usage context is given.

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