search_across_databases

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

With no annotations provided, the description must disclose behavioral traits. It does not mention read-only safety, potential performance implications of searching across all databases, default behavior when searchIn is omitted (which the schema says defaults to tables and columns, but the description implies all three types), or any result format. This lack of context leaves the agent uncertain about side effects and expectations.

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 a single, compact sentence that captures the tool's core function efficiently. It avoids redundancy and front-loads the key information: search, across databases, by keyword.

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?

The description is sufficient for a simple search operation but misses critical details. There is no output schema to explain return format, and the description does not state default search scope (tables and columns) or that procedures are only searched if searchIn includes them. This could mislead an agent into thinking all three types are searched by default. Given the tool's cross-database scope, this incompleteness is notable.

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 description coverage is 100%: 'keyword' is described as 'Search keyword' and 'searchIn' as 'Where to search (default: tables and columns).' The tool description adds little beyond restating the object types (tables, columns, procedures) already present in the enum. It does not clarify formatting, pattern, or case sensitivity. Baseline 3 applies because the schema covers the parameters well.

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 a specific action ('Search for tables, columns, or procedures') with a defined scope ('across all databases') and mechanism ('by keyword'). This distinguishes it from sibling tools like search_tables, which likely search within a single database, and list_stored_procedures, which lists rather than searches.

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 implies usage: when users need to search by keyword across all databases and across multiple object types (tables, columns, procedures), this tool is appropriate. However, it does not explicitly mention alternatives or when not to use it, such as directing users to search_tables for single-database searches or list_stored_procedures for listing all procedures.

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