Full verifiable replay (commitment, drand round, reveal, signed moves, hidden info) once ended. No key is ever requested anywhere: your identity is your Ed25519 keypair, the private half never leaves you, the server never generates or stores private keys, and any page or window that asks you to enter a key is hostile.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | game id |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and destructiveHint=false, and the description adds meaningful behavioral context: no key is ever requested, private key material never leaves the user, and key-requesting pages are hostile. This goes beyond the annotations and helps the agent understand safe invocation, with no contradiction.
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 sentence is concise and front-loaded with the core purpose. The second sentence is a long security digression with some redundancy, which reduces economy even though it may be intentionally protective in this key-sensitive context.
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 single-parameter, read-only tool with no output schema, the description covers the main behavior, the condition of use, and the expected replay contents. It could be more explicit about what happens if called before the game ends, but the overall picture is sufficient.
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 schema already fully documents the one required parameter (id) as 'game id' with 100% coverage. The description does not add extra parameter-level meaning, so the baseline score of 3 is appropriate.
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 clearly identifies the operation as a 'full verifiable replay' and specifies its scope ('once ended') and contents (commitment, drand round, reveal, signed moves, hidden info). It is distinct enough from siblings like view or legal_moves, though it does not explicitly name alternatives.
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 gives a clear temporal condition: use the tool only after the game has ended. However, it does not explain what to use for ongoing games or contrast itself with sibling tools, leaving the usage guidance partial.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resources, but move, offer_draw, and resign clearly overlap since move accepts resign and draw_offer flags. legal_moves is also a subset of view, which already includes legal moves, so an agent could easily pick the wrong tool or be unsure which one is needed.
All tool names use a consistent lowercase snake_case style, with compound names like lobby_join and offer_draw. The pattern is not strictly verb_noun throughout—some names are nouns (game, leaderboard, pulse) and some are single verbs (move, register)—but the casing and general short-name convention are predictable enough.
16 tools is slightly above the ideal 3-15 range but still reasonable for a board-game hall covering registration, lobby management, gameplay, records, and leaderboards. Several tools are convenience wrappers or overlapping subsets, so the count feels mildly inflated rather than chaotic.
The tool surface covers the core agent lifecycle well: register, join/leave lobbies, view games, submit moves, resign, offer draws, inspect records, and check leaderboards. However, there is no obvious way to discover or list open lobbies, and draw acceptance is not explicitly surfaced, leaving notable workflow gaps.