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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description gets a lower bar. 'Nothing is sent' does add one fact annotations cannot express precisely: no payload is pushed to the external system even though openWorldHint=true means a remote lookup is likely. It still omits what happens on remote failure, latency, or why results come back in an arbitrary/'tool's own' vocabulary.

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 short sentences with no filler, and the core action is front-loaded before the read-only reassurance. It is efficient, though the terseness tips into under-specification rather than tightness.

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 tool with an undocumented nested parameter and no output schema, the description should say what the returned column list looks like and how 'selection' scopes it. Instead it leaves the caller guessing about both the input object and the shape of the result, which is a real gap given the open-ended 'tool's own words' phrasing.

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% and one of the two required parameters ('selection') is a free-form nested object with additionalProperties=true, meaning nothing anywhere explains its shape or contents. The description never mentions 'selection' or 'connection_id', so it fails to compensate for the coverage gap beyond loosely implying that a destination is addressed.

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 verb 'Reads' and the resource 'columns or properties a destination has' give a workable sense of the operation, but 'destination' is never tied to the connection_id parameter and the qualifier 'in the tool's own words' is opaque. It also does nothing to distinguish itself from nearby siblings such as list_your_fields, get_reconciliation_fields, or list_connection_destinations, which an agent could easily confuse with this.

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?

There is no statement of when to call this versus the many field- and destination-related siblings, and no prerequisites (e.g., that a connection/destination must already exist). 'Nothing is sent' hints it is safe to call freely, but that is the only usage signal present.

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