df_refresh_cache

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

Annotations already signal readOnly=false, destructive=false, idempotent=true. The description adds concrete context by naming what gets destroyed (the cached state) and what gets re-fetched (RMD snapshot), which goes beyond the structured fields without contradicting them.

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?

A single, front-loaded sentence with no filler. Every phrase adds information: the resource, the scoping option, and the refresh action.

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?

The description plus annotations are sufficient for a basic cache-refresh call, but the 'global' scope value, the role of the language parameter, expected side effects on subsequent reads, and return value are left unexplained. Without an output schema, that gap weakens completeness.

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 only 50%: scope and language lack descriptions. The description adds minimal parameter meaning via 'or the whole project' hinting at scope but does not explain 'global' scope, the language parameter, or how project_id/version_id relate to the refresh. It does not compensate for the undocumented optional parameters.

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?

Description uses a specific verb ('Drop') and names the precise resource ('cached state of a project version or the whole project') plus the re-fetch action. This clearly separates it from sibling read tools like df_get_rmd and destructive tools like df_delete_version.

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 implies the use case—refreshing a stale cache—but never states when to choose this over alternatives or when not to use it. No explicit exclusions are provided, so an agent must infer the appropriate context.

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