digest_declassifiedReturn the most-recently-published Declassified cases over a rolling window. Use for 'what's new in Declassified this week' style prompts. window=today (~24h) | week (default) | month. Public — no auth required.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| window | No | week |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint. Description adds rolling window behavior (today/week/month) and clarifies public access. No contradictions. Lacks details on return format or pagination, but annotations cover safety profile.
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?
Three sentences, front-loaded with action, no fluff. Every sentence adds value: purpose, use case, parameter details, auth status.
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?
Sufficient for a simple tool with 2 params and no output schema. Covers purpose, usage, parameters, auth. Could mention return type (list of cases) but implied. Sibling tools provide context.
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?
Description explains window parameter options but not limit. Schema provides defaults and constraints for both parameters. With 0% schema description coverage, description compensates partially but not fully (limit undocumented).
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?
Clearly states 'Return the most-recently-published Declassified cases over a rolling window,' specifying verb and resource. Differentiates from siblings like get_declassified_case (single case) and search_declassified (search) by emphasizing recency and rolling window.
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?
Explicitly says 'Use for "what's new in Declassified this week" style prompts,' providing clear use context. Also notes 'Public — no auth required.' Does not explicitly list alternatives or when not to use, but context is strong.
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 distinct purposes, but there is overlap between `get_my_private_feed`, `subscribe_topic`, and `list_subscriptions`—all return or manage feed URLs, which could confuse an agent. Otherwise, categories like publisher, fund manager, and search tools are clearly separated.
All tools use consistent snake_case with a verb_noun pattern (e.g., `get_article`, `search_articles`, `publisher_upload_audio`). Exceptions like `digest` are single-word verbs but still fit the pattern. No mixed conventions are present.
With 37 tools, the server exceeds the 25-tool threshold considered 'too many' by the rubric. While the broad scope (news, podcasting, publishing, fund management, embedding) justifies a large surface, the count still adds cognitive load and would benefit from splitting into separate servers.
The tool set covers the major domains: search, retrieval, subscriptions, publishing, fund manager operations, and embedder network. Minor gaps exist, such as the absence of an unsubscribe or delete-episode tool, but the core workflows are well-supported and agents can accomplish most tasks.