show_tables

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

Describes it as safe and provides return type (dictionary with results/errors), but with no annotations, more behavioral traits (e.g., no side effects, performance) could be disclosed. Adequate but not rich.

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?

Concise, front-loaded with purpose, includes Args and Returns sections. Every sentence is earned, no redundancy.

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 simple listing tool with 2 optional params and no output schema, description fully covers purpose, parameters, and return structure. Sibling context is clear.

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 has 0% description coverage, so description adds value: explains database as name and filter with example. Clear and useful, though filter syntax could be more precise.

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?

Clearly states 'List available Databend tables in a database', specifying verb, resource, and context. Distinguishes from siblings like show_databases and describe_table.

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?

Mentions it's a safe operation not affected by safe mode, but lacks explicit when-to-use vs alternatives. Usage is implied by purpose, but no exclusion guidance for tools like execute_sql.

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