Agent Farm

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'Workers can run shell commands (find, du, grep, etc.) for real analysis' which implies execution capabilities, but doesn't disclose critical behavioral traits like whether this is a read-only operation, potential system impact, permission requirements, or rate limits. The description is insufficient for a mutation-capable tool with zero annotation coverage.

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 appropriately sized with four sentences that each add value. It's front-loaded with the core purpose, followed by worker capabilities, parameter explanations, and usage context. There's minimal redundancy, though the parameter explanations could be more integrated with the main description flow.

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 tool with 3 parameters, 0% schema coverage, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, how workers coordinate, error handling, or the scope of 'deep analysis'. The mention of synthesis with qwen2.5:14b is helpful but insufficient for overall completeness.

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?

With 0% schema description coverage, the description partially compensates by explaining 'target_path: Directory/path to analyze', 'analysis_type: 'full', 'redundant', 'sizes', 'cleanup'', and 'synthesize: If True (default), uses qwen2.5:14b to synthesize findings'. However, it doesn't fully document all three parameters' semantics, particularly the specific meanings of analysis_type values beyond listing them.

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 performs 'deep analysis swarm using WORKERS with exec_cmd for thorough system analysis' and lists specific use cases like finding redundant files, cache sizes, disk usage, and log files. This provides a specific verb ('deep analysis swarm') and resource ('system'), though it doesn't explicitly distinguish from sibling tools like 'system_health_swarm' or 'recon_swarm'.

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 implied usage context with 'Use this for finding: redundant files, cache sizes, disk usage, log files, etc.' but doesn't explicitly state when to use this tool versus alternatives like 'system_health_swarm' or 'chunked_analysis'. It gives general application areas but lacks specific guidance on tool selection.

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