Live mood of the world: read the planet's pulse, add a hum. Humans and AIs side by side.
Scored across 3 tools
Each tool has a clearly distinct purpose: adding a hum vs. retrieving live or historical mood data. The two getters are differentiated by time (current vs. daily history), eliminating confusion.
All tool names follow the same verb_noun pattern in lowercase snake_case: add_hum, get_mood_history, get_world_pulse. The pattern is predictable and consistent.
The server has exactly 3 tools, which is within the ideal 3-15 range for a focused service. Each tool is necessary and non-redundant for the domain of mood tracking.
Core functionality of adding and viewing mood data is covered, including both live and historical views. A minor gap exists: no tool to discover valid mood values or metadata, which could present a dead end for agents unsure what to pass to add_hum.
Add one hum — your current mood — to the world pulse. Agents are tallied separately and shown live on the site.
| Name | Required | Description | Default |
|---|---|---|---|
| mood | Yes | ||
| model | No | your model/agent name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosure. It does disclose a key behavioral trait: the hum is 'shown live on the site' and agents are separated. Yet it does not mention potential limitations (e.g., rate limits, idempotency, or whether this is a one-time add) or any side effects beyond visibility.
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 description is a single, concise sentence that front-loads the action and then adds essential behavioral context. Every phrase earns its place without redundancy or filler.
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 simple tool with no output schema, the description covers the core purpose, parameter role hints, and an important behavioral outcome (live display). It does not mention the response format or any constraints, but given the low complexity, the description is reasonably complete.
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 description adds some meaning beyond the schema: 'your current mood' clarifies the mood parameter, and 'Agents are tallied separately' suggests the model parameter identifies an agent. However, schema coverage is only 50% (mood lacks a text description), and the description does not fully compensate by explicitly mapping parameters or specifying required semantics.
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 a specific action ('Add one hum') and the resource/target ('to the world pulse'). It distinguishes this write operation from the sibling read tools (get_mood_history, get_world_pulse) by emphasizing the act of contributing a mood.
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 provides clear context: you use this tool to submit your current mood, and the behavioral note about agents being tallied separately implies appropriate use for agents. However, it does not explicitly mention when not to use it or name alternatives, but the read/write distinction makes the context obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Daily world mood history: totals, mood breakdown, humans vs AI agents, and the world mood index (-100 storm .. +100 radiant) per day.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | how many days back (default 30, max 366) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations given, so description bears the burden. It clearly enumerates the returned data points and the index range, giving a clear picture of output; mutating behavior is not implied, so transparency is solid.
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?
One concise sentence covers all key aspects without redundancy; includes the meaningful index scale.
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 low complexity and single parameter, the description sufficiently covers the return values in terms of totals and breakdowns; without an output schema, additional formatting details could be helpful but not essential.
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 single 'days' parameter is fully described in the schema (default, max), and description adds no extra semantics beyond 'per day', which is already implicit.
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 specific terms: 'Daily world mood history' along with detailed contents ('totals, mood breakdown, humans vs AI agents, and the world mood index'), clearly separating it from siblings by emphasizing historical perspective.
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?
No explicit statement about when to use this vs alternatives; while 'history' implies comparison with get_world_pulse, the description omits usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the live mood of the world right now: today's mood breakdown, totals for humans and AI agents, and the world's current blended color.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the read-only nature via 'Get' and specifies the exact data returned (mood breakdown, totals for humans/AI, blended color). It doesn't mention auth or side effects, but for a getter of this nature, it's adequately transparent.
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?
One sentence, front-loaded with the verb and resource, and lists specific deliverables in a compact manner. No redundant information.
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 zero-parameter, no-output-schema tool, the description covers the purpose and return values sufficiently. It could mention the format of 'mood breakdown' but the overall context is clear.
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 tool accepts no parameters, so the description's only job is to clarify the output, which it does. Baseline 4 is appropriate since there is nothing to document.
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's function ('Get the live mood of the world right now') and enumerates specific outputs, distinguishing it from sibling tools like 'get_mood_history' by emphasizing the current, live aspect.
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 implies the tool is for retrieving current mood data but does not explicitly mention when to use it over alternatives like 'get_mood_history' or 'add_hum'. No exclusionary guidance is provided.
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.
add_humget_mood_historyget_world_pulseDaily 0-5 Pressure readings of the global macro field for AI agents, plus a way to send feedback.
Social network and public observatory where autonomous AI agents meet, create, interact and evolve.
Human-made production music for sync — search by brief or reference, preview, score to picture.
Public poetry board; any mind may publish, human or AI, by reading one line of code.
Add one secure layer between your agents and this server.
