Skip to main content
Glama

Immersive Commons

by com.immersivecommons

Say whether you got a sponsor's credits (yes / stuck / not interested)

ic_hack_credits_mark

Tick one square on your credits checklist. got means you have it. blocked means you tried and it did not work, and IT IS A REQUEST FOR HELP: it puts you on the organisers' help queue with your note, and somebody comes and fixes it. skipped means you do not want this one, which is a fine answer and keeps you off that queue. Marking again OVERWRITES, so flip blocked back to got the moment the booth sorts you out — nothing is appended and there is no history. note is only kept on blocked; put the actual symptom in it (the coupon field says already redeemed) rather than a restatement of the state. THIS DOES NOT CLAIM ANYTHING: it records what happened, it does not make a credit appear, and an agent that marks got without having gone to the vendor has told the room a false thing. Only offers with claimable:true can be marked. YOU MUST HAVE A SEAT: a caller not on the roster gets not_found, and the fix is a seat, not a retry. Args: { eid?, offer_id, state, note? }. Returns: { ok, offer_id, mark, summary }. Required scope: hack:register (any tier), plus a seat on the roster.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eidNo
noteNoWhat went wrong, in your builder's words. Kept only on `blocked`.
stateYesgot = I have it. blocked = I tried and I am stuck, send help. skipped = I do not want this one.
offer_idYesFrom ic_hack_credits_list, e.g. 'tavily'.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations are all false, so the description carries the full burden. It thoroughly discloses overwrite behavior (Marking again OVERWRITES, no history), note retention only on 'blocked', that it does not claim anything but merely records, and that a false 'got' would be a lie. This goes far beyond annotations, covering side effects, preconditions, and ethical constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence provides critical behavioral or usage information. It is well-structured, front-loading the core concept and then delivering details on overwrite, scoping, and prerequisites. While it could be slightly tighter, the density is necessary for a tool with this many edge cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite lacking an output schema, the description specifies the return shape ({ ok, offer_id, mark, summary }) and covers all major aspects: parameters, prerequisites (claimable:true, seat on roster), overwrite semantics, note constraints, and scope requirement (hack:register). For a mutation tool with complex behavior, nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning to parameters: it explains the state enum with clear semantics, clarifies that the note is kept only on 'blocked' and should contain the actual symptom, and indicates offer_id comes from ic_hack_credits_list. However, the optional 'eid' parameter is not elaborated in the schema or description (it appears only in the Args list), leaving a small gap despite 75% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The title and description clearly state the tool's purpose: marking whether you got a sponsor's credits, with explicit state values (got/blocked/skipped). It distinguishes itself from sibling read-only tools like ic_hack_credits_list by focusing on the mutation action ('Tick one square on your credits checklist'), making it unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit conditions for use: only offers with claimable:true can be marked, and a caller must have a seat on the roster (otherwise not_found is returned). It also clarifies when not to use it (e.g., don't retry without a seat) and the meaning of each state, preventing misuse like marking 'got' without visiting the vendor.

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

All Immersive Commons toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools are clearly scoped to distinct actions (e.g., ic_hack_apply vs. ic_hack_register, ic_rooms_create vs. ic_rooms_join). A few pairs could confuse an agent: floor10_submit_highlight vs. floorcast_push both submit HighlightStories but to different queues, and ic_directory_search / ic_agent_directory_lookup / ic_admin_list_members overlap in searching members. Overall, the long descriptions help disambiguate, but the volume requires careful reading.

Naming Consistency3/5

The dominant pattern is ic_<domain>_<verb>_<object> (e.g., ic_admin_list_pending_events, ic_headsets_checkout), but there are notable deviations: floor10_* and floorcast_* prefixes break the ic_ convention, and a few tools use noun-style names (ic_health, ic_capabilities, ic_donations_total). Verb placement also varies (get_* vs *_get, e.g., ic_get_my_membership vs. ic_membership_set_profile). Still, most names are readable and predictable.

Tool Count1/5

175 tools is an extreme count for a single MCP server, far beyond the 50+ threshold that indicates an unwieldy surface. While the platform covers many domains (events, files, hackathon, headsets, prints, rooms, etc.), bundling everything into one server makes discovery and selection difficult. This would be better split into several narrowly-scoped servers.

Completeness4/5

The tool set covers nearly every lifecycle for each domain: CRUD for files/folders, full hackathon admissions and judging, headset lending with waivers and incidents, print farm submission and handoffs, and room coordination. Minor gaps exist: no delete for files/folders, no cancel for events, and some actions (like revoking a Z.ai key or tearing down a room) are explicitly left to human console use. Overall, the surface is remarkably comprehensive for the stated scope.

Resources