The observatory's ruled findings — each with its claim and its falsification test — plus the public corrections log (what we published, then corrected, never deleted). Call this to cite what has been established, or to see where we were wrong. No arguments.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It offers some behavioral context by stating the corrections log is 'what we published, then corrected, never deleted' and that it is 'public,' implying non-destructive and accessible. However, it does not disclose return format, pagination, or any side effects, leaving gaps typical of a minimal viable description.
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 two sentences with no fluff. The first sentence defines what the tool returns, the second gives usage context and confirms no arguments. Every word earns its place, and 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?
For a no-argument list tool with no output schema, the description is sufficiently complete. It describes the content (findings, falsification tests, corrections log), the purpose (citing established knowledge or past mistakes), and the public nature. It does not explicitly state the return type, but the use case implies a list of entries. Given the low complexity, this is nearly 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 tool has 0 parameters, so the baseline is 4 per the rubric. The description explicitly states 'No arguments,' which reinforces the empty schema. Since schema coverage is 100% (vacuously), there is no additional parameter meaning needed, though the explicit statement adds a small clarity bonus.
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 lists the observatory's ruled findings with claims and falsification tests, plus the public corrections log. It provides a specific verb ('list') and resource ('observatory's ruled findings'), and distinguishes itself from server-focused sibling tools (check_server, find_servers, registry_pulse) by focusing on findings and corrections.
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 gives explicit context for when to use the tool: 'Call this to cite what has been established, or to see where we were wrong.' It does not mention alternatives or when-not-to-use, but the purpose is clear enough that the context is unambiguous, especially given the distinct sibling names.
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 clearly distinct purpose: should_i_use gives a quick verdict, check_server provides full evidence, find_tools searches by need, resolve_server_name handles name resolution, registry_pulse is a snapshot, changes_since is a diff, report_call sends feedback, and list_findings lists established findings. No two tools are easily confused.
Most tools follow a verb_noun pattern (check_server, find_tools, list_findings, report_call, resolve_server_name), but 'changes_since' and 'should_i_use' deviate, and 'registry_pulse' is noun_noun. The mixed conventions are still readable and predictable overall, but not perfectly uniform.
Eight tools is a well-scoped number for an observatory server. Each tool covers a distinct aspect of the lifecycle: discovery, decision, investigation, reporting, and ecosystem awareness. No tool feels redundant or missing.
The tool surface fully covers the verifier's domain: get a verdict (should_i_use), deep evidence (check_server), search by need (find_tools), resolve fuzzly names (resolve_server_name), ecosystem stats (registry_pulse), changes over time (changes_since), user feedback (report_call), and public findings (list_findings). There are no obvious gaps in the workflow.