server_guard

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

Description aligns with annotations (idempotentHint, non-destructive). Adds behavioral context: 'start installs guard as remote cron (checks disk/RAM/CPU/audit every 5 min)', 'stop removes guard cron entry', 'status shows...threshold breaches'. No contradictions with annotations.

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, efficient and front-loaded. First sentence states purpose, second details actions, third notes prerequisite. No fluff.

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?

Given complexity (2 params, no nested objects, output schema exists), description covers all needed: actions, parameters, preconditions. Output schema reduces need to explain return values, but description still mentions status output details.

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%, so baseline 3. Description adds value: for 'server' param it notes 'Auto-selected if only one server exists', for 'action' it repeats enum but clarifies outcomes. Provides useful context beyond schema.

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?

Clear verb 'manage' with specific resource 'autonomous security monitoring daemon'. Lists three actions: start, stop, status. Distinguishes from siblings like server_audit or server_doctor by specifying it's a cron-based guard daemon.

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?

Explicitly states 'Requires SSH access to target server' and describes each action's effect. Implicitly suggests when to use by contrast with siblings, but does not explicitly list when not to use or name alternatives.

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