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 already declare the tool as read-only, idempotent, and non-destructive. The description adds value by explaining the recommendation logic (based on goal or time), which goes beyond the annotations. No contradictory behavior is implied.
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, well-structured sentence that front-loads the core purpose and includes key details (goal/time basis, returned fields). 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?
Given the tool's simplicity (one optional parameter, output schema present), the description fully covers what the tool does, when to use it, and what it returns. No gaps remain.
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 input schema has 100% description coverage, including the enum values and the behavior when omitted. The tool description does not add new parameter information beyond what is already in the schema. Baseline score of 3 is appropriate.
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 explicitly states the tool recommends a sound healing session based on goal or time of day, and lists the returned fields. This clearly distinguishes it from sibling tools, none of which provide similar session recommendations.
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 and parameter documentation explain that omitting the goal parameter yields a time-of-day recommendation, providing clear guidance on when to use each option. However, it does not explicitly mention when not to use the tool or suggest alternatives.
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.
Tools are mostly distinct across categories (radio, local info, spiritual, listener management), but there is notable overlap: get_emergency_alerts and get_nws_alerts both provide alerts, and get_or_create_listener overlaps with register_listener. Also, get_chakra_frequencies, get_chakra_guide, and get_solfeggio are very similar. While descriptions help differentiate, agents may still struggle to select the right tool.
All tool names consistently use lowercase snake_case with a verb_noun pattern (e.g., get_weather, submit_song_request, log_listener_history). The verbs are predictable (get, search, submit, log, register, update) and there are no deviations like camelCase or inconsistent verb styles.
With 45 tools, the set is overgrown for a radio station server. Many tools are hyper-specific (e.g., separate tools for chakra frequencies, guide, and solfeggio; moon phase, sun times, and stargazing conditions). Consolidating similar functions would reduce cognitive load and improve coherence.
The tool set covers a broad range: radio operations, listener management, local news/weather, outdoor guides, spiritual content, etc. However, there are notable gaps: no tool to fetch full news articles (only headlines), no way to manage show schedules, and no donation or station info tools. Also, listener profile management is split across multiple tools, which feels incomplete.