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

No annotations are supplied, so the description bears the full burden, yet it says nothing about whether this is a pure read, whether the stream must exist first, or what happens on an unknown stream. It only implies a retrieval operation via the word "Columns".

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 sentence is short enough that nothing is wasted, but it is an incomplete fragment rather than a front-loaded, informative statement. Brevity here comes at the cost of specification.

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?

With no annotations, no output schema, and an undocumented parameter, the description should explain the return shape (e.g. a column list with types) and any prerequisites. As written it leaves the agent to discover output format and stream-reference conventions by trial.

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 single parameter "stream" has 0% schema description coverage, and the description only alludes to it with the phrase "of a stream". It adds no meaning about expected format, naming convention, or whether the value is an ID, a fully qualified name, or a catalog entry.

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?

"Columns and types of a stream" identifies the resource (a stream) and the aspect retrieved (columns and types), so the intent is inferable. However, it is a noun fragment with no verb, and it gives no differentiation from siblings such as catalog_streams or sql_query that an agent might otherwise pick.

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 guidance on when to call this versus catalog_streams (which likely also enumerates streams) or sql_query (which could also reveal column names). The agent must guess the selection condition from the name alone.

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