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

No annotations are provided, so the description carries the full burden. It does add a genuinely useful behavioral detail — '(LIMIT 0 scan)' — which tells the agent this is a cheap, non-destructive metadata read that returns no rows. It says nothing about what happens with an unregistered or misspelled table name, nor about cost on large catalogs, so the disclosure is partial.

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?

One sentence, front-loaded with the payload (what is returned) and finished with the cost mechanism. Nothing is padded or redundant.

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 single-parameter metadata read with no output schema, the description usefully enumerates the return fields itself, so the agent knows what to expect. The only gap is error/edge-case behavior for an invalid or missing table name.

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 100% and the single parameter's schema text already documents both its meaning and its default ('the first registered table'). The description adds nothing about the parameter, which is acceptable at baseline 3 but is a missed opportunity to note default-resolution behavior.

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 ('Return') and enumerates exactly what comes back: column names, Arrow data types, nullability, scoped to a registered table. That is far more precise than a generic 'get schema'. It does not name or differentiate from siblings like column_statistics or list_tables, which keeps it at 4 rather than 5.

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 reach for this tool versus column_statistics, list_tables, or query_sql. The phrase 'for a registered table' hints at a prerequisite, but the agent must infer the workflow (inspect schema before writing SQL) entirely on its own.

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