where_are_records

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: the border-shift caveat that the result is often not today's archive, and the reverse-lookup capability. It does not explain return shape, but an output schema exists, so that is acceptable.

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 opening sentence is long and wraps the core purpose inside a parenthetical list of record types and a geographic enumeration, delaying the verb-resource statement. The second sentence adds value but the whole is one dense block rather than front-loaded. It is not bloated, but structure 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 two parameters (one required, one enum), an output schema, and readOnly/openWorld annotations, the description supplies the missing domain context: the border-shift problem and bidirectional lookup. An agent can call this correctly. The only incompleteness is the undocumented lang parameter, which is minor.

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 exactly 50%: the place parameter is well documented with examples in the schema, but lang has only an enum and default with no description. The narrative in the description compensates partly by explaining what place can represent (province or region, historical or modern), which is meaningful, but the lang parameter remains undocumented in text. Baseline 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 states a specific function — mapping a place (historical province or modern region) to the archives that hold its records — and names the record types and the geographic scope, so the resource is clear. It does not, however, contrast itself with siblings like find_sources or place_history, which is the main thing keeping it out of the top score.

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?

It gives a clear context for use — when you have a province or region and need to know which archive currently holds its records. The bidirectional note (historical province to archive, and modern region back to historical provinces) helps an agent decide the right input. No explicit when-not-to-use or named alternative, so it stops short of a 5.

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