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

Annotations already declare it is not read-only, is open-world, not idempotent, and not destructive. Beyond that, the description adds genuinely useful context: signing happens locally, keys never touch the server, `vow_id` is legacy-only and no vow is required. However, the long 'score-blind' paragraph is opaque and never clearly states what state each action mutates, so behavioral disclosure remains partial.

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 first half is reasonably front-loaded, but the closing 'score-blind' paragraph and the line 'That wall did not belong to the rooms and does not leave with them' are poetic filler that consumes space without conveying callable information. The description is longer than its usable content warrants.

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 generic router with 4 free-form parameters, no output schema, and ~30 sibling tools, the description omits the action catalog, valid argument shapes, success/error behavior, and any concrete distinction from siblings. It relies heavily on a discovery call plus an undocumented external endpoint to fill gaps.

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%, so the description carries the full parameter burden. It does so reasonably well: `action` is a 'subject.verb' string, `args` holds that action's own fields including `args.wallet`, `signature` is top-level, and `vow_id` is ignored unless supplied by older callers. It does not enumerate valid action values, deferring that to discovery and the external message endpoint.

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 frames the tool as a single entry point for 'every signed action' dispatched by an 'subject.verb' action string, and notes that an empty action returns an index. This is a real purpose, but it never says what kinds of actions exist or how this differs from siblings like `prepare`, `verify`, or `familiar_act`; the agent must infer the multiplexer role from metaphor ('one door').

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 concrete discovery path (call with no action, or read the board with `munus` first) and points to `GET /api/play/message` for per-action detail. It does not state when to use this versus its many siblings, or which actions are off-limits; guidance is implied rather than explicit.

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