Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
Scored across 2 tools
The two tools, temporal_peek and temporal_tick, have clearly distinct purposes: one reads state without advancing, the other advances the clock. Their descriptions explicitly contrast their roles, eliminating ambiguity.
Both tools follow a consistent snake_case pattern with the 'temporal_' prefix, making them predictable and easy to distinguish.
With only 2 tools, the server is minimal but tightly focused on its core functionality. It could benefit from additional tools like reset or configure, but the count is not inappropriate for a narrow domain.
The server covers basic read and advance operations, but lacks features like resetting time, configuring tick intervals, or querying history. While sufficient for simple use cases, there are notable gaps for more complex temporal workflows.
Read the current temporal snapshot for a thread WITHOUT advancing state. Use this when you want the gap delta but the call is not the canonical per-turn event.
| Name | Required | Description | Default |
|---|---|---|---|
| tz_name | No | ||
| client_id | No | ||
| thread_key | No | ||
| tz_offset_minutes | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the key behavior (non-advancing state) but lacks details on side effects, permissions, or rate limits. Adequate but not thorough.
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 concise sentences that front-load the main purpose and usage condition, with no unnecessary words.
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?
The description covers core purpose but fails to explain parameter meanings or return value, which is critical given no output schema and 4 undocumented parameters.
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 has 4 parameters with 0% description coverage, and the tool description provides no explanation or context for any parameter, leaving the agent to guess.
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 it reads a temporal snapshot without advancing state, and distinguishes from the sibling tool temporal_tick which likely advances state.
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?
Explicitly says when to use: when wanting the gap delta but not the canonical per-turn event. This provides useful context, though could be more explicit about when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Advance the temporal clock for a thread and return a snapshot (now / prev / gap / day_rollover / fresh_thread). Call once per user turn. Pass a stable thread_key (e.g. the conversation ID) so gap deltas remain meaningful across page reloads.
| Name | Required | Description | Default |
|---|---|---|---|
| tz_name | No | Display name for the timezone (e.g. 'MDT'). Cosmetic; appears in the rendered header. | |
| client_id | No | Namespace tag (e.g. 'caweb', 'cursor'). Defaults to 'mcp'. | |
| thread_key | No | Stable thread identifier within this client. For claude.ai web use the conversation ID; for other MCP clients any caller-stable string. If omitted, falls back to the Mcp-Session-Id header. | |
| tz_offset_minutes | No | Caller's UTC offset in minutes (e.g. -360 for MDT). Used for day_rollover detection and header formatting. Defaults to 0 (UTC) so day rollover is always honest even if the caller forgets to pass one. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool mutates state (advances clock) and includes details like ensuring gap deltas remain meaningful. With no annotations provided, it adequately carries the transparency burden.
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?
Three sentences, each essential: core action, call frequency, and parameter guidance. No fluff, information is front-loaded.
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?
Given the lack of an output schema and annotations, the description covers the main functionality, usage constraints, and return components. It could detail the snapshot structure more, but the listed components are 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?
Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by explaining the purpose of thread_key for stable identification across reloads. Other parameters are not elaborated, but the extra context justifies a 4.
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 states the tool advances the temporal clock for a thread and returns a snapshot with specified components (now, prev, gap, day_rollover, fresh_thread). The verb 'Advance' and the resource are specific, and the action implicitly distinguishes it from the sibling 'temporal_peek'.
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 provides clear usage context: call once per user turn and pass a stable thread_key. However, it does not explicitly compare with the sibling tool or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
temporal_peektemporal_tick
Add one secure layer between your agents and this server.