search_tools

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

With no annotations, the description carries the full burden. It discloses that pinned tools are excluded, that direct calls to hidden tools will fail, and that they must be called via call, batch, or execute. This is significant behavioral information beyond a simple search function, though it doesn't detail edge cases like regex matching nuances or performance.

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 three sentences, each with a distinct purpose: scope definition, output/detail guidance, and invocation warning. It is front-loaded with the core action and is entirely free of filler.

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 tool has a simple two-parameter interface, an output schema (so return values are handled there), and the description covers the search scope, detail levels, and the critical invocation constraint. An agent has everything it needs to correctly search and then call hidden tools.

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%, so the baseline is 3. The description adds value by explaining the default 'brief' output and the alternative of using detail='detailed' or get_schema for richer schemas, but the parameter descriptions in the schema already cover the meanings. It doesn't introduce new semantics beyond what the schema provides.

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 states a specific verb and resource: 'Search hidden tools by regex', and adds a critical scoping detail (pinned tools excluded). It differentiates from siblings by implying that get_schema is for schema retrieval, not search, and that call/batch/execute are for invocation. This leaves no ambiguity about the tool's core function.

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 gives clear context: it explains how to use the detail parameter and suggests get_schema as a follow-up for full schemas. It also warns that hidden tools must be invoked via call, batch, or execute, and that direct calls will fail. While it doesn't explicitly contrast with list_targets or list_databases, the primary usage scenario is well-defined.

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