Search provisions

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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: the searched corpus switches at 2026-07-27 (32024R1689 with recitals vs consolidated 02024R1689-20260727), and per-result applicability is derived from the deadline table. It does not mention pagination or ranking caveats, which keeps it below a 5.

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?

Front-loaded with the core operation and result shape, then the version-selection rule, then the negative scoping clause. Dense but every clause is load-bearing; slightly long as a single paragraph where the version-switch detail could be tighter.

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?

With no output schema, the description still enumerates the returned fields (citation, heading, snippet, score, applicability) and explains the version-dependent corpus, so an agent knows both what it gets back and why results vary by as_of. Nothing needed to call it correctly is missing.

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, and the description goes further by explaining that as_of selects the version searched and that results carry applicability on that date – semantics not conveyed by the pattern description alone. query and limit semantics are left to the 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?

States a specific verb and resource ('Full-text search (BM25) over the AI Act') plus the exact return contents, and explicitly contrasts itself with interpretation/obligation tools ('Finds provisions by wording; it does not interpret them or say which one applies to a system'). An agent can distinguish this from aiact_obligations and aiact_get_provision without opening any schema.

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?

Gives a clear usage boundary: use it to find provisions by wording, not to interpret them or determine applicability to a system. It stops short of naming the alternative sibling tool (e.g. aiact_obligations) that should be used instead for interpretation, so the routing is implied rather than explicit.

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