Recommend skip scan indexes

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

Annotations already declare readOnlyHint=true, so the description adds value beyond that by detailing behavior: returns an empty list on version/driver failure, the effect of the `max_leading_ndv` parameter, and the structure of the return list. No contradiction with annotations. Could be improved by noting that it only queries metadata and has no 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 concise (about 6 sentences) and front-loaded with the primary purpose. It includes an example call, and each sentence adds necessary information without excess. No redundant or vague statements.

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?

Given the tool's complexity (PG version dependency, output structure, parameter meaning, related tools), the description covers all aspects: what it does, when it returns empty, what the output contains (including field names and types), and how to interpret parameters. The output schema is described in sufficient detail, so no gaps remain.

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 coverage is 50% (only `database` has a schema description). The description compensates by explaining `max_leading_ndv`: 'caps the leading-column NDV that's considered low enough for skip-scan to be profitable.' This adds semantic meaning beyond the schema's type and default. The `database` parameter is already described in the schema, so no extra value needed.

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 tool's purpose: 'Find composite B-tree indexes whose leading column has low NDV — these are the ones PG 19's skip-scan optimisation unlocks.' It identifies the specific verb 'Find' and resource 'composite B-tree indexes', and distinguishes itself from siblings by mentioning how its output feeds into `recommend_index_drops` and pairs with `get_skip_scan_status`.

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 provides explicit usage context: it explains that the tool returns an empty list on PG ≤ 18 or driver failure, and suggests pairing with `get_skip_scan_status` for diagnostics. It also connects the output to `recommend_index_drops`, indicating a workflow. However, it does not explicitly contrast with other recommendation tools like `recommend_indexes`, but the intent is clear enough.

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