工具面装卸（按组按需加载工具）

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

Annotations declare idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds valuable context beyond these: the medium-risk note ('会改变目标状态或占用共享资源'), the caching caveat (client tool lists may be stale, re-pull tools/list), and the immediate tool-surface change behavior. This enriches the agent's understanding of side effects and failure modes beyond what annotations convey.

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 information-dense and every section earns its place (group list, caching caveat, small-context model), but it is presented as a long continuous block of text with minimal visual hierarchy. Bold markers help somewhat, yet the density makes it hard to scan quickly. It would benefit from bullet points or clearer section separation while retaining the same content.

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-value documentation is not required. For a metadata/config tool of this complexity, the description is thorough: it covers available groups, action semantics, caching workaround, always-retained tools, and the nano startup path. Minor gaps remain around explicit response format and the distinction from tools_load, but nothing critical is missing for correct invocation.

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 0% and the two parameters have no enums or descriptions. The description compensates fully: it explains action=status/load/unload with concrete examples (toolsets=mem,trace, toolsets=all, toolsets=nano) and enumerates all valid group values with meanings. The agent can invoke this tool correctly without any additional parameter documentation.

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 a specific purpose: dynamically load/unload tool groups to manage context, listing all 11 groups plus the nano profile. It clearly differentiates the core concept (group-based tool surface management) from siblings by explaining the default-core-then-load-on-demand model, and explicitly names the always-retained tools (list_tools / get_version / capabilities / toolset). The verb-resource pair (load/unload groups) is precise and distinguishes it from tools_load and tools_groups.

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 explains the overall model (default core group, load others when needed) and the small-context pattern, referencing tools_groups() and tools_load() as alternatives. However, it creates ambiguity: the small-context section recommends using tools_load() for loading while this tool itself supports action=load, without explicitly stating when to prefer one over the other. Context is present but exclusions/alternatives are not crisply delineated.

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