Maa Fight

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

No annotations are provided, so the description carries the full behavioral burden. It does add one genuinely valuable guarantee beyond the schema: it will never spend Originite Prime to replenish sanity. But it says nothing about blocking/long-running behavior, what happens when sanity runs out, or failure handling — gaps that matter for an 8-param mutation-style task.

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?

Two short lines with the purpose front-loaded and the safety caveat second — nothing wasted. The caveat earns its place because it constrains how the agent may use medicine/count parameters, though it restates the absence of a schema field rather than describing present ones.

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?

An output schema exists, so return values needn't be explained, and all parameters are documented in the schema. Still missing for a long-running, potentially blocking task: prerequisites (game running, account state), what timeout=600 governs, and how client_type interacts with failures. Adequate but with clear gaps.

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 description coverage is 100%, with every parameter (addr, count, stage, series, timeout, medicine, expiring_medicine, client_type) documented in the schema itself. The description adds only the negative clarification about the absent Originite parameter, which is a useful semantic boundary but not parameter detail beyond the schema. Baseline 3 applies.

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 and resource: '运行战斗任务（刷关卡）' — running a combat/stage-farming task, which is concrete and actionable. However, it does not distinguish itself from combat-adjacent siblings like maa_copilot, maa_roguelike, maa_paradoxcopilot, or maa_reclamation, so the agent must infer which combat entry point applies.

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 purpose ('刷关卡' / farm a stage) implies when to use it, but there is no explicit statement of when to prefer this over maa_copilot or maa_roguelike, nor any prerequisite guidance (e.g. whether maa_startup must run first). Usage is only implied.

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