compass_freshnessThe date of the last editorial review ("last verified") for every playbook and guide — transparency about how fresh the advice is.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety traits. The description adds context about transparency and scope ('every playbook and guide'), but does not disclose format details or potential latency. It does not contradict 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?
The description is a single, front-loaded sentence that clearly conveys the tool's purpose without 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?
For a tool with no parameters and no output schema, the description adequately explains what the tool returns (date of last editorial review), though it could specify the output format. Overall, it is sufficient for simple usage.
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?
With zero parameters, schema coverage is 100%, and the description does not need to add parameter info. Baseline is 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 provides 'the date of the last editorial review' for 'every playbook and guide', specifying a concrete verb (provides transparency) and resource (freshness info). It distinguishes from siblings like compass_find_playbook (search) and compass_get_content (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?
The description implies the tool is for checking content freshness but does not explicitly specify when to use it versus alternatives like compass_get_content. No when-not-to-use guidance is provided, but the tool's simplicity reduces the need for extensive guidelines.
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.
Each tool has a clear, distinct purpose: finding playbooks, checking freshness, retrieving content, listing situations, and getting reporting channels. There is no overlap or ambiguity.
Most tools follow a consistent 'compass_verb_noun' pattern (e.g., compass_find_playbook, compass_get_content), but compass_freshness uses a noun instead of a verb, causing a minor inconsistency.
With exactly 5 tools, the set is well-scoped for a digital safety guidance server, covering searching, listing, retrieving content, checking freshness, and getting reporting channels without being too sparse or bloated.
The tool set provides a comprehensive coverage for the domain: listing all situations, searching by user description, retrieving full content, checking content freshness, and obtaining reporting channels. No obvious gaps for a read-only repository.