codelattice_cache

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

The description adds meaningful context beyond the annotations: it discloses that the cache is optional and that its absence does not affect correctness. However, it does not explain side effects or consequences of the clear or prewarm operations. The annotations already signal this is not a read-only tool, and the description does not directly contradict them.

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 two sentences with no filler. It front-loads the critical caveat ('optional performance layer, NOT availability gate') and then gives a concrete usage directive. Every clause earns its place.

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?

There is no output schema, so the description should clarify what each mode returns or changes, but it only explains the status mode. The behavior of clear, explain, and prewarm is left to inference, and the compact parameter is entirely unexplained. For a tool with four modes and no output schema, this is not complete enough.

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 schema documents mode with an enum and the minimal phrase 'Cache operation', while compact has no schema description at all. The description adds semantic value for mode=status but says nothing about the compact parameter or the meaning of clear/explain/prewarm. With schema coverage at 50%, this is only a partial compensation.

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 clearly identifies the tool as cache management and enumerates the exact operations (status, clear, explain, prewarm). The phrase 'optional performance layer, NOT availability gate' sharply distinguishes it from the analysis-oriented sibling tools. An agent can immediately understand the resource and scope.

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 explicitly frames the cache as optional and explains that a disabled persistent cache does not block fresh static analysis, so an agent knows not to treat it as an availability dependency. It also gives a concrete directive: use mode=status to check memory and persistent cache state. It does not detail when to use clear/explain/prewarm, but the main context is clear.

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