semantic_search_mediaSearch images and videos semantically. Returns captions, frame descriptions, or transcript segments — minimal tokens.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Limit to images or videos | |
| query | Yes | Natural language search query | |
| top_k | No | ||
| document_ids | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, non-destructive behavior. The description adds useful behavioral context beyond annotations by stating that results are captions, frame descriptions, or transcript segments and that the output is intentionally minimal in tokens. It does not contradict 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?
The description is a single, well-structured sentence with the core action front-loaded and the return behavior stated immediately. Every phrase earns its place 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?
With four parameters, no output schema, and several closely related sibling tools, the description is too minimal. It leaves out how top_k and document_ids affect results, when to prefer this tool over semantic_search or get_relevant_frames, and the exact shape of the returned results.
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 description coverage is only 50%, and the description adds no parameter-level meaning. It does not explain top_k or document_ids, and while query and type are documented in the schema, the description does not compensate for the undocumented parameters.
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 states a specific verb and resource: 'Search images and videos semantically' and clarifies the return types (captions, frame descriptions, or transcript segments). It is clear and distinct from a generic semantic search, though it does not explicitly name a sibling alternative.
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 implies the tool is for semantic search over media content, but it does not say when to choose it over sibling tools like semantic_search, get_media_description, or get_relevant_frames. No exclusions or alternative routing are provided.
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 resource-action pairs, but the media tools overlap somewhat: get_relevant_frames, get_media_description, and semantic_search_media can all return frame or transcript content. The descriptions clarify scope, but an agent could briefly hesitate before choosing between them.
The set mostly follows a verb_noun pattern like list_user_documents, get_chunk, and summarize_document. However, semantic_search and semantic_search_media break the pattern by leading with an adjective, and list_user_documents uses a redundant 'user_' prefix that list_media does not.
Ten tools is well-scoped for a document and media vault assistant. Each tool addresses a distinct retrieval or summarization need without excessive redundancy or padding.
Search, list, summarize, compare, and media description workflows are well covered. However, get_chunk requires both document_id and chunk_id, and no tool enumerates chunk IDs or retrieves a full document's text, creating a potential dead end for agents that need complete document contents.