Fetch a cached optimized variant of a skill or file without re-running optimization. Useful when an agent wants the lean version for inference but the raw version for editing.
Fetch a cached optimized variant of a skill or file without re-running optimization. Useful when an agent wants the lean version for inference but the raw version for editing.
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | ||
| skill_id | No |
Changes observed during successful MCP inspections.
v0.9.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It implies a read operation but never states it, and gives no guidance on cache-miss behavior (error vs. regenerate), permission requirements, or whether the cached variant can be stale. These are material behaviors for a 'cached' fetch 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?
Two dense sentences with zero filler, and the core purpose is front-loaded ahead of the usage hint. Efficient and readable.
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 a 2-param tool with no annotations, no output schema, and 0% schema description coverage, the description should at least clarify param selection and cache-miss behavior. It does neither, so an agent could invoke it with neither ID or with both and have no idea what to expect.
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 coverage is 0% and neither file_id nor skill_id is documented. The phrase 'of a skill or file' loosely maps to the two params but does not explain the required/optional relationship (0 required), mutual exclusivity, or ID format, so it barely compensates for the coverage gap.
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+resource ('Fetch a cached optimized variant of a skill or file') and adds the key constraint 'without re-running optimization,' which implicitly separates it from optimization.run/dryRun. It does not explicitly name those siblings, so it falls short of a 5.
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 phrase 'Useful when an agent wants the lean version for inference but the raw version for editing' implies a usage scenario, and the no-re-run clause hints at the alternative (optimization.run). But there is no explicit when-to-use/when-not statement or named alternative, leaving the agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.