Table stats

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context by revealing the data comes from system.parts (a ClickHouse system table), but says nothing about permissions, behavior on empty/non-existent tables, or the meaning of 'time range'.

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?

A single front-loaded sentence listing the returned metrics with no filler. It is a noun fragment rather than a full sentence and 'time range' is left undefined, 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?

With no output schema, the description does list the return fields, which partly compensates. However, it omits units, format, and how 'time range' is derived, so an agent lacks enough detail to interpret the response fully.

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?

Both parameters (database, table) are fully documented in the schema at 100% coverage, so the description has no burden to explain them. It adds no parameter-specific information, which is acceptable here but yields only the baseline score.

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 names the specific measurements returned (part count, row count, on-disk size, time range) and discloses the source table (system.parts), so an agent knows exactly what data comes back. It stops short of differentiating itself from siblings like describe_table or server_metrics, and never explicitly states it operates on a given database/table.

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 when-to-use guidance and no mention of alternatives such as describe_table, show_create_table, or server_metrics. The agent must infer that this is the tool for physical/part-level metrics rather than schema or cluster information.

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