pg_readonly

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

Annotations already mark the tool as read-only and idempotent. The description adds crucial details: always runs in BEGIN READ ONLY, SQL write attempts are rejected by PostgreSQL, parameter types for arrays/JSON, and result truncation behavior with a truncated flag. No contradictions.

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?

Approximately 6 sentences, each serving a distinct purpose: core behavior, use cases, safety, parameter guidance, truncation. Front-loaded with the key guarantee. No redundant or unnecessary text.

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?

For a tool with 2 parameters, no output schema, and rich annotations, the description covers all essential aspects: execution model, security, parameter types, result limits. No obvious gaps remain.

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 covers both parameters fully (100% coverage). The description enhances by explaining params are positional ($1, $2), listing accepted types (strings, numbers, booleans, null, arrays, objects) and their PostgreSQL mappings (arrays for ANY, objects for jsonb). Adds value beyond schema.

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 runs SQL statements guaranteed read-only within a BEGIN READ ONLY transaction. It lists specific SQL commands (SELECT, EXPLAIN, SHOW, VALUES) and contrasts with sibling tools like pg_query, making its purpose 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?

Explicitly advises to use this tool 'whenever the goal is to read' and includes examples of appropriate SQL. It warns that PostgreSQL itself rejects writes, and mentions safe auto-allow for permission-gating hosts. Also recommends using params for injection safety.

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