query_dataset

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

With no annotations, the description carries full responsibility for behavioral disclosure. It explains critical format requirements: time periods use 'YYYY|CODE' with code meanings, geographic levels include NAT/REG/LA/SCH, and locations use a specific 'LEVEL|id_type|id_value' format with an example. It also describes the data scope. This goes beyond the schema and gives the agent the context needed to call this read-only query tool correctly, though it doesn't mention pagination or response structure.

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 concise and well-structured: a purpose statement, a prerequisite instruction, a scope statement, and format clarifications. Each sentence earns its place with no redundant filler. For a tool with 8 parameters and multiple format requirements, this length is appropriate and 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?

The description plus fully-described schema provides sufficient context for correct invocation: it identifies prerequisite metadata, data domains, and all key parameter formats. It lacks explicit details about pagination behavior and response shape, but the schema includes page/page_size fields and there is no output schema to detail. Given the tool's complexity, this is reasonably complete, though a note on filter semantics would elevate it.

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%, providing a baseline of 3. The description adds semantic enrichment beyond the schema: it expands the meaning of time codes ('AY' = academic year, 'CY' = calendar year), and provides a concrete location example ('LA|code|823'). This depth helps the agent understand the format in a way the schema's terse field descriptions do not.

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 explicitly states 'Query a DfE Explore Education Statistics dataset with specific indicators and filters', using a specific verb (Query) and resource (DfE dataset). This clearly distinguishes it from sibling tools like compare_schools or search_schools, which serve different purposes. It also lists the data domains (absence, exclusions, performance, etc.), reinforcing its unique role.

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 an explicit prerequisite: 'Use get_dataset_metadata first to discover available indicator and filter IDs.' This guides the agent on when to use this tool relative to its metadata companion. However, it does not explicitly mention when not to use this tool or name alternative query tools (e.g., search_education_statistics), so it lacks that exclusionary guidance.

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