databutler-uk-exams

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

With no annotations, the description must carry behavioral disclosure. It usefully reveals that the tool returns links to the board's page rather than hosted PDFs and gives the copyright rationale. However, it does not mention the read-only nature, output format, or any failure or availability behavior.

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 one front-loaded sentence with a relevant parenthetical explanation; there is no redundant wording. It could be improved by defining 'spec' more explicitly, but as written it is compact and readable.

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 no annotations, no output schema, and three unconstrained string parameters, the description is too sparse. It leaves the return shape, valid parameter values, and the boundary against the sibling tools unstated, so an agent may invoke it incorrectly.

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 0% and the description adds no meaning to board, level, or subject. There are no accepted values, value formats, or relationships between the parameters, so an agent cannot reliably know what strings to supply.

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 names a specific deliverable: official past-paper archive links pointing to the board's own assessment-resources page. It is clear about the resource and the no-PDF-hosting constraint, though it does not explicitly distinguish itself from the sibling tools.

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?

There is no guidance on when to use this tool instead of exam_spec_lookup or exam_topic_paper. 'Per spec' hints at the input context but does not state use cases, exclusions, or prerequisites.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the contents of the metadata but not the tool's behavior: whether it requires parameters, supports partial lookups, returns multiple results or a single spec, or has any default/fallback behavior. The read-only nature is implied by 'lookup' but not explicitly disclosed.

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 sentence with no filler and front-loads the core concept ('UK exam specification metadata'). The list of covered fields is compact but somewhat dense; however, it earns its place by signaling the tool's scope.

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?

Given no annotations, no output schema, and no parameter descriptions, the definition is not complete enough for an agent to invoke the tool with confidence. It does not explain what a successful response looks like, whether all parameters are optional, or how to narrow a lookup. The sibling tools are not addressed, leaving potential routing ambiguity.

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 input schema has 0% description coverage and no enums, and the description does not explain the board, level, or subject parameters. Although the parameter names are somewhat self-explanatory, the description does not define acceptable values, how parameters combine, or whether they are optional. The description lists metadata categories but does not connect them to the parameters.

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 names a specific resource ('UK exam specification metadata') and lists concrete contents (spec codes, paper structure, topics, links), so an agent can tell what the tool returns. It lacks an explicit verb like 'look up' but the tool name and content make the purpose reasonably clear. It is not explicitly differentiated from sibling tools, though the metadata list helps.

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?

No guidance is provided about when to use this tool versus exam_paper_index or exam_topic_paper. There is no statement of intended use, filtering strategies, or exclusions. The description merely states what metadata is available, leaving usage entirely implied.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It goes beyond the schema by listing the return payload, revealing a known quirk about AQA Combined Science Trilogy Physics Paper 2, and explicitly scoping coverage to specific AQA specs. It does not describe behavior for unsupported topics, but the disclosed constraints are substantial.

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 front-loaded with the purpose and remains tight despite covering multiple aspects: purpose, example, input, output, quirks, and supported specs. The example sentence earns its place by clarifying the tool's intent, and the coverage list is necessary for setting expectations. There is no redundancy or 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?

Given that there is no output schema and no annotations, the description sufficiently explains what is returned, what inputs are accepted, and which specifications are supported. It also communicates a known quirk that could otherwise surprise an agent. The definition is complete enough for an agent to select and invoke the tool correctly.

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 meaningful value by listing the exact covered specifications, which clarifies valid combinations of board, subject, and level. It also reinforces that board, subject, and level are optional alongside the required topic parameter, slightly exceeding what the generic schema examples provide.

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 immediately states the tool's core purpose in the form of a concrete question: which exam paper a topic is on. It then specifies the resource and result set: returns the paper, sibling topics, spec code, and official spec URL. This clearly distinguishes it from sibling lookup tools by focusing on topic-to-paper mapping.

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 for when to use the tool: when a user has a topic and wants to know which exam paper it appears on. It also frames this as the canonical student revision question, signaling the intended use case. It does not explicitly name alternatives or state when not to use it, but the context is specific enough.

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