search_instances

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

No annotations are provided, so the description carries the full burden. It discloses that the tool performs searching, supports partial matching and case sensitivity, and returns detailed information with pagination. It does not mention any destructive behavior, rate limits, or ordering, but overall provides good transparency for a search tool.

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 structured with a clear header, bulleted functions, args, and returns, but it is somewhat verbose. It could be more concise by removing the bullet list of functions and integrating them into a single sentence. The structure is readable but not maximally efficient.

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 covers the core functionality, explains all 5 parameters, and mentions output (list with pagination metadata). There is an output schema (not shown), so the description need not detail return fields. However, it lacks information on error conditions, authentication requirements, or behavior when no results are found. Overall, it is largely complete for a search tool.

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?

The schema has 0% description coverage, meaning the properties have no descriptions. The tool's description provides an 'Args' section that explains each parameter, including defaults and allowed values (e.g., search_in defaults to 'name', case_sensitive defaults to false). This fully compensates for the lack of schema descriptions, adding significant meaning beyond the bare 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 it searches for OpenStack instances based on various criteria, listing specific fields (name, status, host, flavor, image, availability zone). It clearly distinguishes from sibling tools, which are mostly get_* tools for specific resources, by offering a search with partial matching and pagination.

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 for searching instances by criteria, mentions 'efficient pagination' and 'optimized for large-scale environments', but does not explicitly state when to use this tool vs alternatives like get_instances_by_status or get_instance_by_name. It lacks explicit 'when not to use' or comparative guidance.

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