Search Japanese / English-language SaaS Terms of Service snapshots (Stripe / Anthropic / AWS / Google Cloud / GitHub …). Stage 1 covers 'terms' docs. Each hit includes firstSeenAt and ledgerVerified.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | タイトル / 本文先頭抜粋・部分一致 | |
| vendor | No | 'stripe' / 'anthropic' / 'aws' / 'gcp' / 'github' … | |
| docType | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that search covers 'terms' docs and each hit includes firstSeenAt and ledgerVerified, but does not mention read-only nature, rate limits, or other behavioral traits.
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 concise sentences with no wasted words. First sentence states purpose and examples; second adds stage scope and hit metadata.
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?
No output schema; description mentions hit content (firstSeenAt, ledgerVerified) but fails to explain the four input parameters (limit, query, vendor, docType). The tool's search capabilities are under-specified.
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?
Schema coverage is 50%; the description does not explain the query, vendor, or docType parameters. It adds no meaning beyond the schema's existing Japanese descriptions, which are already present.
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 searches Japanese/English-language SaaS Terms of Service snapshots, lists example vendors, and specifies it's for 'terms' documents in Stage 1. This distinguishes it from siblings like tos_watch_get or tos_watch_timeline.
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?
Implied usage for searching snapshot content, but no explicit when-to-use or alternatives. Siblings are not mentioned, so the agent must infer when to use search vs. other TOS tools.
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.
Most tools have clearly distinct purposes, especially the ledger-watch groups with domain prefixes. However, there are near-duplicate utilities such as content_authenticity_domain_reputation and domain_intel_reputation, and fx_tax_convert overlaps with price_oracle_fx_rate/convert. The sheer number of tools also increases the chance of selecting the wrong one, though descriptions are generally clear.
The naming is largely consistent with a <domain>_<action> or <domain>_<watch>_<action> pattern, and all names use snake_case. Minor deviations include standalone names like entity_search, kyb_report, verify_receipt, and the confusing singular/plural pair of sanction_watch_* and sanctions_screen_*. Overall, the pattern is predictable.
With 172 tools, this server is far beyond the typical well-scoped range. It bundles dozens of unrelated utility domains (weather, carbon, CVE, geo, etc.) alongside the Japan public-ledger watches, making it unwieldy for an agent to navigate. This extreme count is a major coherence problem.
For the core Japan public-ledger domain, coverage is excellent: each ledger has search, get, timeline, recent_changes, and verify_ledger, plus cross-ledger entity_search and temporal_query. The unrelated utility areas are also fairly complete for their own purposes, but the server's scope is so broad that some utilities are duplicated (e.g., multiple currency converters). Overall, no critical dead ends in the main domain.