get_provision_at_date

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It states that the tool returns the complete provision text, validity dates, and optionally the amendment history after the queried date. It also discloses support for historical, current, and future provisions. The description does not mention any side effects, but as a retrieval tool this is expected to be read-only. The main behavior is well-documented, though edge cases or error handling are not addressed.

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 well-structured with a clear purpose statement followed by use cases and a supports list. It front-loads the core functionality and then expands with examples and features. While it is somewhat longer than necessary, every section adds value and no sentences are redundant. The bullet points improve readability, making it effective despite its length.

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 there is no output schema, the description appropriately explains what the tool returns: complete provision text, validity dates, and optional amendment history. It also covers supported date scenarios and examples. However, it does not mention potential error conditions, limits, or how to handle invalid citations, but these are likely covered by sibling tools like validate_citation. For a retrieval tool with clear inputs and outputs, the description is fairly complete.

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?

All four parameters have schema descriptions with examples and patterns, so schema coverage is 100%. The description adds minimal extra context—for instance, it mentions the default for include_amendments and gives an example of provision_ref, but these are already implied by the schema. The description does not significantly enhance parameter understanding beyond what the schema provides, so the baseline of 3 is appropriate.

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 tool's core function: retrieving Finnish statute provision text as of a specific date, explicitly labeled a 'time-travel query.' It distinguishes itself from siblings like get_provision by the temporal dimension, making its unique value obvious. The resource (statute provision), verb (retrieve), and scope (as read on a date) are all specific and unambiguous.

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 concrete use cases with examples (e.g., 'What did Tietosuojalaki 1:3 say in 2019?') that illustrate when to use the tool. It also explicitly lists supported scenarios: historical versions, current version, and future provisions. However, it does not explicitly name alternative tools like get_provision for current text or check_currency for currency checks, relying on inference from context. The guidance is clear but lacks explicit 'when not to use' exclusions.

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