refresh_accounts

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

With no annotations, the description carries the full burden. It does disclose that this mutates cached state ('force a refresh') rather than just reading, which is meaningful. But it omits cost/latency (this is likely a network refetch), what happens if both 'org' and 'all_orgs' are supplied, and behavior on partial failure across orgs.

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; the resource and the two scoping modes come first. Nothing extraneous to trim.

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 tool is simple and an output schema exists, so return values need not be explained. Still, for an unannotated, zero-description-coverage mutation tool, the description leaves the org/all_orgs interaction and the cost of a 'force' refresh unspecified — both of which affect whether an agent should call it.

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 description coverage is 0%, so the description must compensate. It does map the two parameters to intent ('one org, or every configured org'), clarifying that 'org' scopes to a single directory and the alternative covers all configured orgs. However, it never says what 'org' identifies (name vs. id), what the default null means, or how the two flags interact.

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+scope: 'force a refresh of the cached account directory', with the two modes ('one org, or every configured org') made explicit. It is distinguishable from siblings like cache_status or search_accounts, though it never names them directly.

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?

Usage is only implied: the word 'force' and 'cached' suggest invoking it when the cache is stale, and cache_status is the obvious companion tool, but neither the trigger condition nor the alternative is stated. No when-not guidance, e.g. whether calling it repeatedly is wasteful.

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