replication_status

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

Description indicates it's a read operation but lacks details on permissions, empty results, or error conditions. With no annotations, it provides minimal behavioral context.

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?

Extremely concise, front-loaded with purpose, no wasted words.

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?

Returns standbys and replay lag but does not describe response structure; adequate for a simple list but missing details on no-standby scenario.

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 single parameter 'target' is described as 'Target name from config; omit for the default,' adding context beyond the schema's type definition, compensating for 0% schema coverage.

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?

Description clearly states it reads connected standbys and their replay lag from pg_stat_replication, which distinguishes it from siblings like replication_slots and wal_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 [READ] prefix implies safe usage, but no explicit guidance on when to use versus alternatives or when not to use.

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