Recommend indexes

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

The description discloses behavioral traits beyond annotations: it explains that fresh=true bypasses the cache and re-reads live data, and describes the output format (list of objects with specific fields). Annotations (readOnlyHint=true) align with the description, and no contradictions are present.

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 two paragraphs plus an example, which is clear but slightly verbose. It front-loads the purpose and then adds details. Every sentence adds value, but it could be more concise without losing meaning.

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 moderate complexity (3 parameters, no required parameters, output schema described), the description adequately covers usage and behavior. With many sibling tools, it provides enough context for an agent to select and invoke it correctly, though missing explicit comparison to recommend_index_drops.

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 only 33% (only database parameter has a description in schema). The description compensates by explaining fresh (bypass cache) and giving an example with min_live_tuples, adding meaning beyond the schema's default values and types.

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 recommends tables that may benefit from indexing, specifically large tables read mostly by sequential scan. It uses a specific verb ('recommend') and resource ('tables') and distinguishes from sibling tool 'recommend_index_drops' by focusing on indexes to add, not drop.

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 guidance on when to use the fresh parameter (bypass cache after schema change) and includes an example usage. However, it does not explicitly state when not to use this tool or compare it to alternatives like recommend_index_drops, though the purpose is clear.

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