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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the trailing 'Read-only' merely restates them. The one piece of added behavior is the positioning of guides as thorough procedural content versus schemas/errors as minimal correctness data, which helps an agent judge the payoff of calling. Nothing is said about response size or format, so the addition is modest against an already-complete annotation set.

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 content is front-loaded into two dense sentences with no filler, and the parenthetical topic list is an efficient enumeration. It is telegraphic to the point of slight opacity ('Guides on demand'), but nothing is redundant enough to cut.

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 low-complexity read-only retrieval tool with a fully documented schema, this is close to sufficient — the agent knows it gets procedural or reference text. However, with no output schema the description should say what a guide returns (markdown text, size, whether topics overlap) and it leaves the 'script' and 'relations' topics unexplained.

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% with two enums, so the schema already defines every parameter. The description adds meaning for one case only — 'topic=reach says per class what moddl can change' — while duplicating the class/category scoping the schema already documents. The enum values 'script' and 'relations' are never explained, so the description does not fully compensate for what the enum labels alone leave ambiguous.

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 the resource (guides/documentation) and enumerates concrete content: step-by-step workflows for create_building, insert_door, clashes, quantities, bulk_change, plus field reference for filter/report/history and per-class reach. That is specific enough to separate it from siblings like find_elements or run_script. It lacks an explicit verb, but the intent ('retrieve reference documentation') is 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?

'Schemas and errors carry a correct call; guides carry the thorough way' gives a real selection rule: consult guides when you need the complete procedure, not just a valid invocation. It does not state when to avoid the tool or which topic to pick when several could apply, so it falls short of full explicit routing.

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