Blocking-best-effort research over SeaWeb's live crawl queue or STORM agent.
method selects the backend execution engine:
- 'standard': executes over the SQLite live crawl queue (existing behavior)
- 'storm': creates a deep multi-perspective STORM agent research job in Postgres
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | standard | |
| query | Yes | ||
| method | No | standard | |
| wait_s | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly states 'blocking-best-effort', which is a behavioral trait not captured by annotations (annotations have all false hints, except readOnlyHint=false). It also mentions that 'storm' creates a job in Postgres, adding some context. However, it does not disclose that it may block for extended periods or what happens on failure/timeout, which is relevant for a blocking operation.
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 reasonably sized and the method options are clearly listed with a bullet-like structure. However, the first sentence is a bit elliptical ('Blocking-best-effort research over...'), and the method documentation could be more integrated. It's not overly verbose but could be better formatted.
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?
The tool has an output schema, so return values are covered. However, the description omits important details: the meaning of 'depth' parameter, the behavior of 'wait_s' (blocking semantics), and potential side effects (e.g., creating jobs in Postgres). For a complex tool with 4 parameters and a blocking behavior, the description leaves gaps, but the output schema and annotations help.
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 0%, so the description must explain the parameters. It explains 'method' options and their effects, and the description's title 'Blocking-best-effort' implies the wait_s parameter (how long to wait) without naming it. However, it does not explain 'depth' or 'wait_s' explicitly, but given the 0% coverage, the explanation of 'method' adds significant value, warranting above baseline.
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 it performs 'research' over two execution engines (live crawl queue or STORM agent), which is specific and distinguishes it from siblings like 'research_status' (which likely checks status) and 'search_web'. The verb 'research' is specific enough given the context of the tool ecosystem.
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 explains how to select between methods ('standard' vs 'storm') and mentions that it's 'blocking-best-effort', but it does not explicitly state when to use this tool over alternatives like 'search_web' or 'research_status'. It implies usage for deep research via STORM but lacks explicit when/when-not guidance.
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.
There is notable overlap among search, search_web, search_restaurants, and search_salons, as well as between filter_restaurants/filter_salons and search with constraints. However, descriptions clarify the intended vertical or corpus, and entity getters are distinct. The overlap is manageable but could cause misselection.
Names mostly follow a get_/list_/search_/register_/delete_/submit_/vote_ pattern in snake_case. Minor deviations like 'recall', 'remember', 'research', and 'travel_health' are less predictable but still readable. Overall consistent and clear.
38 tools is on the heavy side for a single MCP server, exceeding the typical well-scoped range. While the server covers multiple subdomains (search, travel disruptions, memory, feedback, research), the sheer number may overwhelm agents and suggests potential consolidation.
The tool surface covers core workflows: search and entity retrieval for restaurants/salons, disruption monitoring with standing queries and webhooks (register/list/delete), research submission/polling, and memory/feedback mechanisms. Minor gaps exist (e.g., no cancel for research jobs, no explicit entity list endpoint), but these are workable and do not break typical agent tasks.