Readies a player action against the current revision, returning state, canon, GM context, policy, and pending checks without advancing the story.
Prepare an exact player action against the current revision. Returns state, canon, GM context, policy and all pending checks. Does not advance the story.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| branch_id | Yes | ||
| campaign_id | Yes | ||
| player_action | Yes | ||
| known_policy_sha256 | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover idempotency (true), destructiveness (false), and open-world scope, so the description is not the sole carrier here. It adds useful behavioral context by enumerating what is returned and clarifying that the story is not advanced, but it never explains why readOnlyHint is false (what gets written or persisted) or what happens when the caller's revision is stale, which matters given "current revision" and the known_policy_sha256 parameter.
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?
Three short sentences, front-loaded with the purpose, then the return payload, then the key constraint. Every sentence contributes and there is no filler.
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 output schema, the description helpfully lists what comes back (state, canon, GM context, policy, pending checks), which is real added value. But for a non-read-only tool with five undocumented parameters and no stated ordering relative to commit_turn, it leaves prerequisite, concurrency, and persistence questions unanswered.
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 0% across five parameters, so the description carries the full explanatory burden and fails it. It never mentions query, branch_id, campaign_id, or known_policy_sha256; only the loose word "policy" in the return list hints at the policy hash, and "player action" loosely maps to player_action. Agents get no guidance on concurrency, defaults, or what the two seemingly unrelated inputs (query, known_policy_sha256) are for.
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 gives a specific verb and resource (prepare an exact player action) and scopes it to "the current revision," which is far more than a restatement of the name. It also implies differentiation from commit_turn via "Does not advance the story," though it never names that sibling outright, so an agent must infer the pairing.
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?
Usage is only implied: the statement that it does not advance the story suggests it is a pre-step to commit_turn, but no condition, prerequisite, or alternative is stated explicitly. An agent can guess the workflow but is given no when-to-use rules.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.