Semantic search across your analyzed media library. Returns ranked results with titles, summaries, transcript snippets, labels, and relevance scores. Use this to find previously analyzed media by topic, content, or keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language search query (e.g., "product demo", "interview about AI", "Dallas footage") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so safety is covered. The description adds useful return-format details (ranked results with titles, summaries, snippets, labels, relevance scores) and clarifies the semantic nature, which is valuable beyond 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?
Two concise sentences with no filler. The first sentence states the core action, the second explains return values and usage. Everything earns its place.
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 simple one-parameter read-only search tool with strong annotations, the description sufficiently covers what the tool does and what it returns. No output schema exists, so the explicit mention of result fields is helpful. It lacks only minor details like result limits or pagination, but those are not critical here.
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 already provides a strong description for the 'query' parameter with examples and natural language guidance. The description adds 'by topic, content, or keyword' and 'semantic search', but these mostly reinforce the schema rather than introduce new meaning. Baseline 3 is appropriate.
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 a specific verb ('search') and resource ('analyzed media library'), and distinguishes from siblings like list_media by emphasizing semantic search and ranked results. It communicates the exact purpose without ambiguity.
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 phrase 'Use this to find previously analyzed media by topic, content, or keyword' provides clear context for when to invoke the tool. It does not explicitly mention alternatives or exclusions, but the sibling context makes the intended use obvious.
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 targets a distinct action and resource: analysis jobs (submit, check, get results, download), folder management (create, delete, list, rename), media operations (list, move, search, set visibility), and account info (organization, profile). There is no overlap or ambiguity between tools.
All tools follow the consistent pattern `echosaw_<verb>_<noun>`, using clear verbs like analyze, check, create, delete, get, list, move, rename, search, and set. The naming style is uniform and predictable across the entire set.
With 14 tools, the server covers a well-scoped platform for media analysis and library management. Each tool serves a clear purpose without feeling bloated or sparse, fitting comfortably within the ideal range.
The server covers the full analysis workflow, folder organization, media searching, and account retrieval. Minor gaps exist such as lack of media deletion or job cancellation, but core workflows are well supported and no critical dead ends are apparent.
