anjian_doctor

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the critical safety behavior—that it only reads and inspects, never executing checks against network targets—which is valuable transparency for a 'doctor' tool that might otherwise sound like it runs diagnostics against live systems. However, it doesn't disclose what it does with findings, whether it writes to any state, or what the output looks like. The read-only nature is partially implied but the boundaries of 'external security tools' inspection are unclear.

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 a single sentence that efficiently conveys the tool's scope (read-only), its targets (安鉴台, external security tools, reports), and a critical exclusion (no network target checks). No wasted words, and the negative statement front-loads the safety-critical boundary. It's appropriately sized for a tool with no parameters.

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 zero parameters and no output schema, the description is the only source of information, and it conveys the essential purpose and safety boundary. However, for a tool named 'doctor' (suggesting diagnostics), the description is somewhat thin—it doesn't clarify what a check entails, what constitutes a 'pass/fail' scenario, or how the output would be used. For a simple zero-parameter tool, this is adequate but not rich; more context about what the diagnostic produces would strengthen 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?

The tool has zero parameters, which means there's nothing for the description to elaborate on parameter semantics. Per the baseline rule for zero-parameter tools, a score of 4 would be baseline, but the description adds no meaningful value about what state or context the tool reads from. Since schema coverage is 100% and there are no parameters to document, the description doesn't need to compensate, but it also doesn't provide any additional semantic context beyond the schema, placing it at the baseline-adjacent level of 3.

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 states it performs read-only checks on the 安鉴台 (Anjian platform), external security tools, and reporting capabilities, and explicitly clarifies it does not execute checks against network targets. However, the verb '检查' (check/inspect) is somewhat vague about what specific inspection or diagnosis this 'doctor' tool performs, and while it distinguishes itself as non-targeting, it doesn't clarify how it differs from sibling tools like anjian_capability_plan which may also assess platform capabilities.

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 a partial exclusion (does not check network targets) which helps distinguish a core boundary, but it gives no guidance on WHEN to use this tool versus siblings like anjian_quick_assess, anjian_get_assessment, or anjian_capability_plan. There's no stated context for when a doctor/diagnostic check is appropriate, making it unclear which scenarios should trigger this tool.

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