search_classes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It accurately indicates a read-only search operation ('Find classes') and discloses the return structure (IRIs with labels and comments). It does not describe potential edge cases or exact regex behavior, but for a simple search tool it is sufficiently transparent and non-misleading.

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 extremely concise—three short sentences, each carrying distinct information: purpose, filtering, and return format. There is no fluff or repetition, and the key facts are front-loaded.

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 3 optional parameters and no output schema, the description provides the essential context: what it searches, how it can be filtered, and what it returns. It does not explain repository context or response marshalling, but these are adequately inferred from the description and sibling tools. It is nearly complete, though a 5 would require explicit details on execution context (e.g., selected repository).

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%, as every parameter (limit, pattern, repository_id) has a description. The description adds minimal value beyond the schema—just restating that filtering by name pattern is possible, which the schema already captures. Therefore, baseline 3 is appropriate per the rubric.

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 specific action ('Find classes') and resource ('the ontology'), distinguishing it from sibling tools like search_properties and find_instances. It also specifies the key capability of filtering by name pattern and the return format (IRIs with labels and comments), leaving no ambiguity about purpose.

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 provides clear context: it is for finding ontology classes, optionally filtered by name pattern. It does not explicitly mention alternatives or when not to use this tool, but the context is strong enough to infer its role among siblings. Lacks explicit exclusions or comparisons, so not a 5.

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