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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds a behavioral trait annotations cannot express: by default it answers from a local copy, and refresh re-reads from the provider. That caching distinction is exactly the kind of extra context worth having.

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?

Two sentences, no filler, with the core output stated first and the parameter caveat second. The phrase 'with the channel IDs you name in a post' is slightly dense, but nothing is wasted.

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 no-required-param read tool with full schema coverage and no output schema, the description covers what is returned and the one behavioral quirk (local copy vs provider re-read). Return shape details are minor given the tool's simplicity, though a hint about pagination or account fields would fully close the gap.

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 100%, so the baseline is 3, and the schema already explains refresh as 're-read from the provider before answering.' The description goes further by naming the triggering scenario (a person has just connected something), which tells the agent when the flag is warranted rather than just what it does.

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 states the resource clearly ('the owner's connected accounts') and what it yields ('the channel IDs you name in a post'), which implicitly separates it from list_platforms (available platforms rather than connected accounts). It lacks an explicit verb, but the name plus the resource phrase make 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?

It gives a real conditional for the refresh flag ('after a person has just connected something'), which is genuine usage guidance for the parameter. However, it never says when to call this tool versus siblings like list_platforms or whoami, so the routing guidance is implied rather than stated.

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