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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the substantial security transparency is handled. The description adds useful context about returned account properties (capabilities), but it does not disclose output format, pagination, or the exact meaning of identity/health flags. It also introduces 'capability flags' without linking them to the input or output schema, which creates slight confusion. No contradiction with annotations.

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 short, with no verbose filler. The first sentence is informative and the second gives a practical use-reminder. However, the second sentence is slightly ambiguous and could mislead an agent into expecting a capability-flags input parameter, which is not present in the schema.

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 simple, read-only listing tool with only two well-documented parameters and a rich annotation block, the description is nearly sufficient. It outlines what data the tool exposes and gives a target-selection workflow hint. It is missing an explicit return-value shape or note on how 'capability flags' map to other tools, but for this complexity level, the description is adequately complete.

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?

The input schema fully explains both parameters (request_id as an echoed tracing field, workspace_id as conditionally required). With 100% schema coverage, the description does not need to explain them, but it also adds no method hint. The phrase 'capability flags' does not correspond to any schema parameter, so the description does not assist with parameter meaning.

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 identifies the resource as connected accounts and conveys a listing operation, especially through the title 'List Connected Accounts'. It distinguishes itself from sibling list tools (e.g., list_posts, list_workspace_assets) by enumerating account capabilities: identity, health, and publish/inbox/comment/insight.

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 gives a practical use hint ('Use capability flags to choose targets'), implying this tool is a starting point for selecting accounts. However, it does not explicitly state when to prefer this tool over sibling list tools, nor does it give any exclude guidance. The intended usage is therefore more implied than explicitly scoped.

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