get_sound_sessionRecommends a KAZM sound healing session — binaural or tonal — based on the listener's goal or current time of day. Returns session name, description, frequency, duration, and link.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | Listener's intent — omit to get a time-of-day recommendation |
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | ||
| recommended | Yes | ||
| also_available | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare safe, read-only, idempotent behavior. Description adds details on return fields (session name, description, frequency, duration, link) and decision logic (goal or time-of-day). No contradictions.
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 efficient sentences, no redundancy, main action front-loaded. Every sentence adds value.
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 simple input, rich annotations, and presence of output schema, description covers all needed behavioral and input context. No gaps.
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?
Single parameter 'goal' with enum and 100% schema coverage. Description adds critical context: omitting goal yields a time-of-day recommendation, which is not in schema.
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 recommends a KAZM sound healing session based on goal or time, with specific verb 'Recommends' and resource 'sound healing session'. Distinguishes from siblings by being a recommendation tool rather than information retrieval.
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?
Implies usage when a listener wants a session recommendation. Lacks explicit when-not-to-use or alternatives, but no sibling tool provides similar functionality, so context is sufficient.
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.
Many tools have distinct purposes, but there is overlap in areas like listener management (get_listener_profile, get_or_create_listener, register_listener, update_listener_preference, log_listener_history) and alerts (get_emergency_alerts, get_nws_alerts, get_fire_restrictions, get_wildfire_perimeters). This can cause confusion for an agent selecting the appropriate tool.
Tool names mostly follow a verb_noun pattern, but verbs are inconsistent: 'get_', 'search_', 'submit_', 'log_', 'update_', 'register_', 'get_or_create_'. The listener management tools have varying verbs, and there is a mix of specific and generic names. The pattern is readable but not fully consistent.
At 45 tools, the server is overloaded for its stated purpose as a radio station. It covers many unrelated domains (emergency alerts, hiking, chakras, etc.), which would be better split into separate, focused servers. The tool count feels excessive and unfocused.
While the radio-related tools (now playing, requests, schedule, listener management) cover core functionality, the inclusion of many unrelated tools (e.g., hiking trails, chakras, sports scores) dilutes the server's purpose. There are obvious gaps in radio-specific features (e.g., no tool for playlist management or DJ scheduling) but an overabundance of peripheral tools.