cache_propose_invalidate

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

Without annotations, the description carries the full burden. It discloses a key behavior: 'Warns when estimated_affected exceeds 10000.' It also clarifies conditional parameter requirements. However, it does not describe the return value or what happens after proposing (e.g., proposal creation).

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, front-loading the purpose and adding essential details without verbosity. Every sentence contributes meaning, making it highly concise.

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 no output schema, the description covers the tool's core logic and behavior. It lacks explanation of the proposal lifecycle (e.g., that this creates a proposal for review). However, it is adequate for a tool with clear parameter dependencies and a warning.

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 100% schema coverage, the baseline is 3. The description adds value by explaining the conditional logic for filter_expression and filter_value based on filter_kind, and the warning threshold for estimated_affected, which goes beyond the schema's field descriptions.

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 'Propose a cache invalidation for review,' which is a specific verb+resource combination. It distinguishes from siblings like cache_approve_proposal (approve) and cache_edit_and_approve_proposal (edit and approve), making the purpose unambiguous.

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 provides explicit guidance on how to use the tool based on cache type, describing the required filter_kind and corresponding parameters for semantic_cache and agent_cache. It implies the context but does not explicitly state when not to use this tool versus alternatives.

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