get_index_usage

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It names the DMV source, which hints at read-only behavior, but it doesn't clarify whether the tool returns one row per index or an aggregate, whether it reflects cumulative counts since last server restart, or whether it requires elevated permissions (since sys.dm_db_index_usage_stats is a system view often accessible to VIEW SERVER STATE). These gaps leave the agent uncertain about the output format and side effects.

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 description is a single, information-dense sentence that front-loads the purpose and immediately lists the four metrics. The parenthetical about the DMV source is useful and not wasted. There is no redundancy or filler, making it an ideal length for quick parsing by an agent.

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?

There is no output schema, so the description must explain what the tool returns. It lists four counters but does not state the structure (e.g., whether results are grouped by index, whether index name and database are included, or whether all indexes on the table are listed). It also omits that the 'table' parameter is required (though the schema shows it). An agent cannot fully predict the output shape, which is a significant gap for a statistics tool.

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%—each parameter has a short description (table name, schema name with default, server name, database name). The tool description adds no extra meaning beyond those schema descriptions. Per the rubric, with high coverage the baseline is 3, and since there is no additional parameter-specific information, a 3 is appropriate.

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 clearly states the verb (Get) and resource (index usage statistics) and specifies the exact metrics (seeks, scans, lookups, updates) and the source (sys.dm_db_index_usage_stats). This distinguishes it from siblings like get_indexes (which lists index definitions) and get_missing_indexes (which suggests new indexes). It loses a point because it doesn't explicitly say it's per-table, though that's inferred from the required 'table' parameter.

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?

The description gives no guidance on when to use this tool versus alternatives like get_table_stats, get_missing_indexes, or get_indexes. It doesn't mention any prerequisites (e.g., requires table name) or exclusions (e.g., not for missing index suggestions). An agent must infer from the name and parameters when this is appropriate, leaving room for misrouting.

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