forget

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

Annotations are absent, so the description carries the full burden. It does not disclose whether deletion is permanent, whether it requires ownership/permissions, whether an error occurs for missing keys, or how the optional agent scope affects the target entry.

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?

A single short, front-loaded sentence with no filler, but its brevity comes at the cost of under-specification rather than economy.

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?

The existence of an output schema relieves the description of explaining return values, but for a destructive operation with no annotations and zero parameter documentation, the description leaves too much about behavior and targeting unexplained.

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 only `key` is implied by the prose. The second parameter, `agent`, is completely undocumented in both schema and description, leaving its scoping behavior to inference.

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 (删除) and resource (共享黑板上的某个 key), so the agent knows this removes data from a shared blackboard. It does not, however, distinguish itself from siblings like remember/recall, which read or write the same blackboard.

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 use this tool versus remember, recall, or other state-changing siblings, and no mention of preconditions such as whether the key must exist or whether the caller must own it.

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