Search Irish public data

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the set of upstream data sources queried (open-world scope made concrete) and the return shape ('ids like cso:F1001'). It does not mention pagination, result limits beyond max_tokens, or empty-result 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 handoff sentence ('Returns ids ... to pass to fetch') is well placed at the end and earns its keep. The bulk of the text is a 14-item comma-separated source list that is informative for scope but reads as a run-on enumeration rather than front-loaded, prioritized description.

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 2-parameter federated search tool with an output schema present, the description covers scope, sources, and the id format needed to chain into fetch, which is the key integration detail. Missing pieces are minor: no result-count expectations or behavior when a provider is unavailable.

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% and both parameters (query, max_tokens) are documented in the schema with examples and ranges. The description adds no parameter-level meaning beyond the schema – it does not explain query syntax, provider scoping, or how max_tokens interacts with multi-source results. Baseline 3 is appropriate when the schema carries the load.

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 clear verb ('Search') and resource (Irish public data) and enumerates the 14 federated sources, which pins down scope precisely. It also distinguishes itself from the sibling 'fetch' by stating it returns ids 'like cso:F1001' that are then passed to fetch. However, the enumeration substitutes for a description of what the search actually does (keyword matching? full text?), so it is clear but slightly thin on capability.

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 implies the correct workflow by saying ids are 'to pass to fetch', which is a useful chaining hint. It gives no explicit when-to-use guidance relative to siblings such as ireland_call, ireland_catalogue, or nearby, nor any when-not-to-use or scoping conditions. Usage is therefore implied rather than instructed.

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