agent-tool

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

With no annotations provided, the description carries full behavioral burden. It successfully discloses format support and selection behavior, but omits critical safety information: whether it overwrites existing output files, handles symlinks, preserves permissions, or errors on unsupported extensions. This leaves significant behavioral gaps for a filesystem mutation tool.

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?

Three sentences with zero waste: the first states purpose, the second lists capabilities, and the third explains the format selection mechanism. Information is front-loaded and each sentence earns its place. No redundancy or fluff present.

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 2-parameter tool with complete schema coverage and no output schema, the description adequately covers the core functionality. However, it lacks edge case documentation (behavior with unsupported extensions, empty source arrays, or existing output files) that would make it complete for safe agent operation.

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%, establishing a baseline of 3. The description adds valuable semantic context beyond the schema by explaining that the 'output' parameter's file extension determines the compression format—a crucial usage detail not present in the parameter description itself. This elevates the score above baseline.

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 opens with a specific verb ('Compresses') and clear resources ('files and directories') resulting in a specific output ('archive'). It effectively distinguishes from sibling 'decompress' by describing the compression direction and from general file tools like 'copy' or 'backup' by specifying archive creation.

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 implicit usage guidance by listing supported formats (.zip, .tar.gz) and explaining the format determination logic ('determined by the file extension'). However, it lacks explicit guidance on when to use this versus siblings like 'decompress' or 'backup', and omits prerequisites such as file existence requirements.

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