lcm_compact

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, and it states only that context compression is 'executed.' It fails to disclose that compaction is likely a mutating operation that alters or discards existing context, whether it is reversible, whether it requires an active session, or what the side effects on stored conversation history are. For a tool whose name implies data modification, this is a significant transparency gap.

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 extremely short and front-loaded with zero wasted words, which is structurally clean. However, brevity crosses into under-specification here — the single phrase earns its place but conveys almost no usable information beyond the tool name.

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?

For an action tool with a default-sensitive 'force' flag, no annotations, and no output schema, the description is severely incomplete. An agent has no way to know what compaction does to the LCM context, when forced compaction differs from automatic behavior, what the result of the operation is, or whether it is safe/reversible. It is inadequate for correct invocation and post-condition assessment.

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% — the 'force' parameter is already documented as '强制压缩' (force compression), so the schema carries the semantic weight. The description adds no further meaning about when or why force should be true versus false, but per the baseline rule, full schema coverage warrants a 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 "[LCM] 执行上下文压缩" (execute context compression) is essentially an expanded restatement of the tool name 'compact' — it adds a generic verb and the resource 'context' but does not specify what compaction actually does to the context (e.g., summarizes, drops old messages, frees tokens). It does not distinguish the tool from its siblings beyond the obvious action-vs-query split, which an agent could already infer from the name.

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?

There is no guidance on when to invoke this tool versus alternatives like lcm_status or lcm_search, nor any indication of when compaction is needed or when the 'force' parameter should be set versus letting the system act automatically. No prerequisites, exclusions, or sibling routing are mentioned at all.

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