clear_cache

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. It explicitly discloses the edge-case behavior: 'Does nothing (and still reports success) when the cache is disabled or the directory does not exist.' It also explains the return value (Dict with success status, cleared_files count, and freed_bytes). It does not mention permission requirements or potential side effects, but for a cache-clearing operation, this is sufficient. The description goes beyond a simple 'clears cache' and gives non-obvious behavior.

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 well-structured: a one-line summary followed by a detailed explanation, and clearly labeled Args and Returns sections. It is concise with no fluff. The main purpose is front-loaded, and the edge-case note is placed early. Every sentence adds value.

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?

Given that there are no parameters and an output schema is present (as indicated by 'Has output schema: true'), the description is complete. It explains the exact behavior, including the no-op edge case, and states what the return value contains. There is nothing an agent needs to know to call it correctly that is missing. The description does not need to repeat return format details since an output schema exists.

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 input schema is empty (0 parameters), so schema description coverage is 100% vacuously. The description mentions an 'Args: ctx: MCP context for logging', which is likely an internal argument, not a user-facing parameter. With no user parameters to explain, the description adds no additional parameter semantics but is not deficient. The baseline for 0 parameters is 4, and the description does not contradict or omit anything relevant.

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 states a specific action: 'Delete all cached render files and report freed space.' It specifies the resource (cached render files) and the exact scope ('every cached image and its dependency manifest'). It is distinct from all sibling tools, which handle checking, exporting, rendering, etc., with no ambiguity.

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 does not explicitly compare against alternative tools or state when to prefer this one. However, the purpose is so specific and self-contained that usage is implied by the name and description. It does not provide when-not-to-use guidance beyond noting behavior when cache is disabled, which is more behavioral than usage guidance. No explicit alternatives are named.

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