reference

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

No annotations are provided, so the description carries the full burden and does so well: it discloses that content is cached, sourced from the game's database with mods and DLC included, served one section per call, that the text is very large (tens of thousands of tokens), that it is mirrored as MCP resources, and that it can be called outside the player's turn.

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 purpose and the usage rule, and most sentences carry unique information. Slight redundancy: the long enumeration of covered content in the opening sentence duplicates the section list that follows, which a reader could skip.

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 annotations and no output schema, the description still covers return format (Markdown), size, caching, alternate resource URIs, and turn-timing constraints, so an agent knows what to expect. It does not spell out error behavior for an invalid `section` value, a minor gap.

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?

The single `section` parameter has 0% schema description coverage, but the description compensates by enumerating allowed values (terrain, resources, improvements, units, buildings, projects, processes, promotions, policies, techs, beliefs, specialists, actions) and stating the one-section-per-call rule. Minor mismatch: the prose names categories like wonders, features and technologies that are absent from the enumerated section list.

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 resource and scope: it returns the game's rule book as Markdown covering every unit, building, wonder, tech, belief, etc., read from the game's own database and cached. It also explicitly distinguishes itself from siblings by noting that no other answer repeats this text (chooser rows carry the enum/name/live numbers instead).

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 condition for use ('read it once at the start of a game if you can hold it, otherwise the section a choice needs') and an alternative delivery channel (MCP resources civ5://reference). It also states a timing constraint ('Usable while it is not my turn') and that sibling tools do not contain this text. No explicit when-not-to-use case beyond the token-size warning.

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