Defend an area by assigning a persistent guard job that shoots approaching enemies, refills turrets, and repairs structures until cancelled.
Persistent job: guard an area — shoot enemies that come near, refill ammo turrets and repair structures from your inventory — until cancelled. Replaces your current jobs.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | ||
| y | No | ||
| radius | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses persistence until cancellation, the job-replacing side effect, the three guard actions, and that inventory is consumed for refills/repairs. It does not state how the job ends beyond cancellation or whether it can coexist with other jobs, but the key mutating behaviors are surfaced.
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?
One tight sentence that front-loads the purpose ('Persistent job: guard an area') and packs behaviors and the job-replacement side effect into the remainder. No filler; every clause adds information.
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?
Behavior and side effects are well covered and an output schema exists, so return values need no explanation. However, parameter semantics are a real gap in a 3-parameter tool where x/y are nullable and defaulted — an agent can call it safely with no args, but cannot target a specific area without guessing. Adequate overall, but not complete.
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 0% and the description never mentions x, y, or radius, so the agent receives no meaning beyond raw schema defaults (null/null/16, radius bounded 8-32). It must guess that x/y denote the area center and radius its size, plus units. The description should have mapped the guarding concept onto these parameters.
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?
States a specific verb ('guard') and resource ('an area'), and enumerates concrete behaviors: shoot enemies, refill ammo turrets, repair structures from inventory. The 'Persistent job' framing plus 'Replaces your current jobs' clearly distinguishes it from immediate-action siblings like fight and from follow_player.
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 persistent/cancellable job framing implies when to use it (ongoing area defense), but no alternative is named and no when-not-to-use guidance is given. An agent must infer that fight is for immediate combat and job_cancel for stopping this job. Guidance is implied, not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.