ic_headsets_admin_mark_oosOperator pulls a unit from rotation. Refuses if the unit is currently lent (force-return first). Appends to the unit's notes with a date stamp + reason. Args: { unit_id, reason }. Returns: { ok, message }. Required scope: admin:headsets_review.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| unit_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds significant context beyond annotations: it declares the refusal guard for lent units, the side effect of appending notes with datestamp + reason, the return format {ok, message}, and required scope 'admin:headsets_review'. Annotations provide destructiveHint and idempotentHint, which align with description.
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?
Four concise sentences front-load purpose, then detail behavior, parameters, and return. No filler or redundancy.
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?
Description covers behavior, conditions, output shape, and required scope. Lacks mention of idempotency (but annotations cover it) and potential error cases. Adequate for a simple admin tool.
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?
Input schema has 0% parameter descriptions. Description only lists parameter names (unit_id, reason) without adding format, examples, or constraints. For a tool with zero schema coverage, more detail is needed to guide correct input.
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?
Description clearly states the tool marks a PICO unit out-of-service, with specific verb 'pulls a unit from rotation'. It distinguishes from sibling tools like ic_headsets_admin_clear_oos (reverse operation) and ic_headsets_admin_force_return (prerequisite action).
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?
Description explains context (operator pulls from rotation) and a precondition (refuses if currently lent, suggesting prior force-return). It does not explicitly compare with alternative tools, but the behavior is clear enough for an admin action.
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 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.
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.
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.
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.