Read PG stat recovery

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

Annotations already provide readOnlyHint=true, so the description's additional details—return format with nullable fields, empty list conditions—add significant behavioral context without contradiction. The description fully discloses edge cases and data structure, exceeding what annotations alone convey.

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 sentences plus an example—extremely concise. Every sentence adds value: first explains purpose, second covers edge cases, example shows invocation. No wasted words, and the structure is front-loaded with the key action.

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 presence of an output schema (not shown but implied), the description adequately covers the tool's behavior, including nullability of fields and empty result scenarios. It also mentions the PG version requirement. For a simple read tool, this is sufficient for an agent to understand when and how to use it.

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 100% with a detailed description of the `database` parameter. The tool description only mentions the parameter in passing, adding no new semantic meaning beyond the schema. Baseline 3 is appropriate as the schema carries the full parameter documentation.

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 returns rows from PG 19's `pg_stat_recovery` view, detailing the specific information (replay progress, lag, startup state). It distinguishes from siblings by focusing on recovery statistics for a standby server, which is a specialized function not covered by other list/read tools.

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 conditions when the tool returns empty results (PG <19, view absent, not in recovery) and mentions the optional database parameter for targeting a secondary. However, it does not explicitly compare to other related tools like `get_wal_archive_status` or `read_pg_wal_stats`, leaving the agent to infer usage context.

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