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

With annotations already covering readOnlyHint, idempotentHint, and destructiveHint, the description adds rich non-obvious behavior: inactive legs are 'hidden from normal UI but never deleted,' there is 'no campaign-level ruleset field,' the summary shape transforms raw ObjectId arrays into resolved [{_id, name}] lists, and imagineWorldIds/imagineAdventures are derived from other objects' links and are read-only here. These disclosures go well beyond the structured annotations.

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 description is long but every sentence carries a distinct fact: precondition, legs structure, hidden-leg behavior, absence of a campaign-level ruleset, detail-mode transform, house-rules semantics, and cross-tool read-only fields. It is front-loaded with the core purpose. It loses half a point because the detail-mode explanation partly repeats the schema's parameter 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?

Despite the tool's complexity — nested legs, dual response modes, derived imagine fields, and cross-tool data flows — nothing an agent needs is missing: membership prerequisite, id semantics, detail behavior, response shape, and downstream linkage (imagineAdventures ids are the valid values for a session's imagineAdventureId). The output schema covers raw return structure, and the description covers everything else.

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. The description adds meaningful value by specifying exactly what the detail modes produce: summary replaces raw rule/item/spell ObjectId arrays with resolved [{ _id, name }, ...] lists 'the LLM can act on,' while full returns the raw ObjectId arrays. It also clarifies that the id parameter selects a campaign the caller must belong to. This exceeds the schema's terse wording.

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 opening sentence is precise: 'Fetch one campaign by id, including settings and any DM/player metadata.' It names a specific verb, a specific resource (campaign), and a retrieval key, and it is clearly distinct from sibling list tools (play_list_my_campaigns) and other get-one tools (play_get_session, play_get_move).

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 states an explicit precondition ('Calling user must be a member (DM or player)') and routes mutations of the imagine fields to named alternatives ('change them with the imagine link/unlink tools'). It also guides the detail-mode choice. It stops short of an explicit when-to-use vs play_list_my_campaigns distinction, but that is strongly implied by 'Fetch one campaign by id.'

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