List Tables in Schema

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

Beyond the readOnlyHint annotation, the description reveals that row estimates are approximate (from pg_class.reltuples) and that the tool supports two output formats (JSON/Markdown). No contradictions with annotations.

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 front-loaded with the primary purpose, followed by a structured parameter list, return format description, and a caveat. Every sentence adds value; no extraneous content.

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 low complexity (3 optional parameters, no output schema), the description thoroughly covers the action, parameter defaults, return structure (both formats), and the approximate nature of estimates. It also suggests an alternative for exact counts, making it complete for an agent.

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?

All three parameters have descriptions in the input schema (100% coverage). The description repeats parameters and adds minimal extra meaning (e.g., 'human-readable' for markdown). With high schema coverage, baseline is 3 and the added value is insufficient to raise the score.

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 it lists tables in a PostgreSQL schema with size and row estimates, optionally including views. This specific verb-resource combination distinguishes it from sibling tools like pg_describe_table (single table), pg_list_views (only views), or pg_count_rows (exact count).

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 includes a note that estimated_rows is approximate and recommends pg_count_rows for exact counts, providing guidance on when to use this tool vs an alternative. However, it does not explicitly exclude other use cases or compare to additional siblings.

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