list_my_messagesRead the authenticated user’s UniAffitti conversations from the same chat used by the web app. Without a conversation_id return fast conversation summaries and last-message previews; with one load the complete recent messages for that conversation.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| unread_only | No | ||
| messages_limit | No | ||
| conversation_id | No | Optional Firebase conversation/thread id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, covering the safety profile. The description adds genuine behavioral value on top: the dual-mode response behavior (summaries/previews vs. complete recent messages) and the web-app data-source context. No contradictions with the annotations.
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?
Two sentences with zero filler. The purpose is front-loaded in the first sentence, and the conditional behavior occupies the second. Every clause earns its place, with no restatement of the title or name.
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 tool with four optional parameters, no required parameters, and annotations covering safety, the description captures the core dual-mode behavior and even hints at return content (summaries/previews vs. full messages). The main omission is the unread_only filter's semantics, and with no output schema present, some return-shape expectations are left to inference.
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 only 25% (only conversation_id is documented). The description compensates for conversation_id by explaining it triggers the full-message mode, and loosely implies limit/messages_limit via 'fast summaries' vs. 'complete recent messages.' However, unread_only is never mentioned in either the schema or the description, leaving a real gap.
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 uses a specific verb and resource — 'Read the authenticated user's UniAffitti conversations' — and adds a useful scoping detail, 'from the same chat used by the web app.' It clearly distinguishes from list_my_favorites/list_my_listings/list_my_requests by resource and from send_room_message by read-vs-write verb, though it never names a sibling explicitly.
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 strong conditional usage context: 'Without a conversation_id return fast conversation summaries and last-message previews; with one load the complete recent messages for that conversation.' This tells the agent exactly what to expect in each mode, but it does not explicitly state when to prefer this over send_room_message or other siblings.
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 distinct by resource and action, but the search/catalog cluster is fuzzy: search_universities, search_cities, list_search_metadata, and list_university_campuses overlap in purpose. search_rooms and rank_room_matches also have a similar discovery role, making it easy to select the wrong tool without careful reading.
All tool names follow a consistent snake_case verb_noun pattern, with verbs like add, list, get, search, create, update, and send clearly indicating the action. This makes the tool surface highly predictable and easy to navigate.
20 tools is on the heavier side, but the count is justified by the broad scope: room search, comparison, ranking, favorites, rental requests, messaging, listing creation, and university catalog browsing. The set remains manageable because each tool maps to a distinct workflow step.
Core room-finding workflows are covered well: search, details, compare, favorites, requests, and messages. However, listing management is incomplete (create_listing has no update/delete) and messaging only supports sending a first message, with no tool for replying to an existing conversation, leaving notable dead ends.