infra_cache

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

Annotations declare destructiveHint=true and idempotentHint=true. The description adds valuable behavioral context that 'clear' can be limited to a specific content_id, and documents return structures (file_count, entries, removed count). However, it omits side effects (e.g., whether clearing affects running analyses) or rate limiting.

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?

Front-loaded purpose statement followed by structured Args/Returns sections. The formatting is scannable and every section serves a distinct purpose. Slight verbosity in 'Returns:' section could be tighter, but overall efficient for a 3-parameter tool with multiple operation modes.

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 the presence of annotations (safety hints) and output schema, the description provides sufficient high-level context. It enumerates the four operation modes and their distinct return shapes (stats vs diagnostics), which is adequate for an infrastructure tool with clear enum-based actions.

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?

With 67% schema coverage, the description compensates effectively: it defines the 'action' parameter (missing schema description) as 'Cache operation — "stats", "list", "clear", or "context"', and clarifies that content_id 'limit[s] deletion' when clearing. It adds the constraint that auth_token is required when INFRA_ADMIN_TOKEN is configured, matching the schema description.

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 opens with 'Manage the analysis cache — stats, list, clear, or inspect context cache state', providing a specific verb (manage), resource (analysis cache), and operation list. It distinguishes from content analysis siblings by positioning itself as infrastructure/maintenance (infra_cache) rather than content processing.

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?

No explicit guidance on when to use this tool versus alternatives. While 'clear' implies maintenance scenarios, the description lacks prerequisites (e.g., 'use when cache is stale') or exclusions ('do not use during active analysis'). The Args section documents parameters but not usage context.

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