clean_runtime_cache

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

With no annotations, the description must carry the behavioral burden. It promises 'safely clean' and not touching vmcp_* artifacts, but doesn't disclose whether actual deletion is the default, what confirmation is required, how dry_run alters behavior, or how include_unknown affects the operation. This is a notable gap for a destructive cleanup tool.

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 a single, front-loaded sentence with no filler. It states the action, the target location, and the key constraint in under 20 words, which is ideal for quick parsing.

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?

Though an output schema exists and no parameters are required, the one-sentence description leaves critical invocation details unspecified: the relationship between dry_run and confirm, the meaning of max_age_hours, allowed values for execution_intent, and the default behavior if confirm is absent. For a cleanup tool with 8 undocumented parameters, this is insufficient even if the purpose is clear.

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?

All 8 parameters have zero schema description coverage, and the tool description only hints at runtime_dir and dry_run through its wording. It does not explain confirm, plan_sha256, max_age_hours, include_unknown, execution_intent, or runtime_identity, so an agent cannot correctly populate them.

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 uses a specific verb ('clean') and resource ('temporary files from the MCP runtime directory'), and adds a distinguishing constraint ('without touching project vmcp_* artifacts'). This clearly separates it from sibling tools like clean_run_outputs and makes the tool's scope instantly understandable.

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 states the context (MCP runtime directory) and explicitly excludes project artifacts, giving a basic sense of when to use it. However, it doesn't name any alternative tools or explain when to prefer a dry run over an actual clean, leaving part of the decision to the agent.

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