What changed in the tool economy since a date: verdict flips, deaths, revivals, new servers, confirmed drift — the census diff as data. Poll this weekly to keep a local view current without re-crawling.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | YYYY-MM-DD; omit for the whole latest diff |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses that the tool returns change data (diff) and lists the categories of changes, making the behavioral scope clear. It does not discuss output format or side effects, but as a read-only query this is acceptable.
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 entire description is one sentence that packs the purpose, content, and usage tip into a compact form. Every phrase is informative, with no 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 single-parameter diff tool with no output schema, the description provides a complete overview: what it returns, when to use it, and the date format. It could benefit from explaining the response structure, but the sibling context and simplicity make it sufficient.
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 schema fully describes the 'since' parameter (YYYY-MM-DD, omit for latest diff), so the baseline is 3. The description reinforces the date concept but adds little beyond the schema, so it doesn't warrant a higher score.
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 identifies the tool as a diff/report of changes in the tool economy since a date, enumerating specific change types (verdict flips, deaths, revivals, new servers, confirmed drift). This distinguishes it from sibling tools like registry_pulse (likely a snapshot) and find_tools (search).
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 explicitly advises polling weekly to keep a local view current without re-crawling, which conveys a clear usage pattern. It also implies this is a delta update rather than a full crawl, though it doesn't name alternative tools for when not to use it.
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.