Index findings

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

Annotations already declare read-only and non-destructive, so the description adds extra value by disclosing that the data source resets with the server and that exclusion rules apply. This behavior is not visible in annotations and is important for interpretation.

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 three sentences, each earning its place: findings, the reset caveat, and the exclusion rationale. It is front-loaded with the most important output information and has no filler.

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?

The description covers the key findings, data freshness caveat, and exclusions, which is fairly complete for a read-only analysis tool. It lacks a description of the return format and does not explain the 'schema' parameter, but overall it gives sufficient context for correct use.

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 description does not mention either parameter. Schema coverage is only 50%, with 'database' described and 'schema' having only a default and no description, leaving the semantics of the 'schema' parameter unclear. The tool description should compensate for this gap but does not.

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 enumerates the tool's outputs (unused indexes, duplicates, profitable sequential scans), which identifies it as an index analysis tool. It does not explicitly use a verb like 'analyze' or 'list', and it doesn't directly contrast with sibling tools, but the scope is unambiguous.

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 important timing guidance: counters come from pg_stat_* and reset with server restart, so they should be read after real traffic. It also explains why primary-key and unique indexes are excluded, which helps the agent know when to trust results. It doesn't mention alternatives explicitly, but the context is sufficient.

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