search_postsSearch Bluesky posts by keyword or phrase. Returns matching posts with author handles, timestamps, engagement metrics, and content.Requires bsky_handle and bsky_app_password in the gateway URL query params.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results (1-100, default 25) | |
| query | Yes | Search query |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "query": "artificial intelligence"
+ },
+ {
+ "limit": 100,
+ "query": "bluesky news"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "oneOf": [
+ {
+ "properties": {
+ "posts": {
+ "description": "Matching posts from search",
+ "items": {
+ "properties": {
+ "author": {
+ "description": "Author's display name or handle",
+ "type": "string"
+ },
+ "createdAt": {
+ "description": "ISO timestamp of post creation",
+ "type": "string"
+ },
+ "handle": {
+ "description": "Author's handle",
+ "type": "string"
+ },
+ "likes": {
+ "description": "Number of likes",
+ "type": "number"
+ },
+ "replies": {
+ "description": "Number of replies",
+ "type": "number"
+ },
+ "reposts": {
+ "description": "Number of reposts",
+ "type": "number"
+ },
+ "text": {
+ "description": "Post content text",
+ "type": "string"
+ },
+ "uri": {
+ "description": "AT URI of the post",
+ "type": "string"
+ }
+ },
+ "required": [
+ "uri",
+ "author",
+ "handle",
+ "text",
+ "createdAt",
+ "likes",
+ "reposts",
+ "replies"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "posts"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "error": {
+ "description": "Error code",
+ "type": "string"
+ },
+ "message": {
+ "description": "Error message with authentication instructions",
+ "type": "string"
+ }
+ },
+ "required": [
+ "error",
+ "message"
+ ],
+ "type": "object"
+ }
+ ],
+ "type": "object"
+}Input schema / examplesRemoved value: -[
- {
- "query": "machine learning"
- },
- {
- "limit": 50,
- "query": "climate change",
- "sort": "top"
- }
-]Input schema / examplesAdded value: +[
+ {
+ "query": "machine learning"
+ },
+ {
+ "limit": 50,
+ "query": "climate change",
+ "sort": "top"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds an authentication requirement (bsky_handle and bsky_app_password) and specifies the returned fields, going beyond the annotations to explain operational context.
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 two sentences with zero fluff. It front-loads the core purpose and then gives the auth requirement. The minor missing space after 'content.' does not detract from the structure or conciseness.
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 is simple (2 params, 1 required) and has an output schema, so the description doesn't need to explain return values. It covers purpose, auth requirement, and general return contents. However, it omits any mention of rate limits or sorting, which could be useful in edge cases, but is not essential for basic operation.
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 100% (query and limit are fully documented). The description adds little beyond what the schema already provides, merely restating the query as 'keyword or phrase' which mirrors the schema's 'Search query'. Baseline 3 is appropriate since schema does the heavy lifting.
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 searches Bluesky posts by keyword or phrase, and itemizes the return fields (author handles, timestamps, engagement metrics, content). This distinguishes it from sibling tools like get_posts or get_thread, which retrieve posts by ID or handle.
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 specifies a prerequisite (bsky_handle and bsky_app_password in the gateway URL) which is useful context, but it does not explicitly state when to use this tool versus alternatives, nor any exclusions. Usage is implied by the nature of a search tool, but no when-not guidance is given.
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 roles, but several overlapping pairs create ambiguity: ask_pipeworx vs ask_pipeworx_beta are explicitly identical today, discover_tools vs suggest_questions both serve discovery/onboarding, and bet_research vs polymarket_edges both address betting-edge questions. The detailed descriptions help, but an agent could still select the wrong tool in these cases.
The set uses at least four naming conventions: get_* for Bluesky reads, verb_noun for Pipeworx tools (ask_pipeworx, resolve_entity, validate_claim), polymarket_* prefixed tools, and verb-only memory tools (remember, recall, forget). Each subgroup is internally consistent, but the overall mix feels inconsistent and unpredictable.
39 tools is well beyond the typical well-scoped server, and the scope sprawls across Bluesky reads, Pipeworx data, Polymarket analysis, memory, subscriptions, and one-off utilities like generate_llms_txt and scan_dependency. The count would be more reasonable split into separate servers; as-is it feels heavy and unfocused.
Within the server's evident scope, coverage is strong: Bluesky read operations, Pipeworx query/research/verification, entity profiling, and subscription lifecycle are all represented. The main gaps are write actions for Bluesky (posting, following, liking) and a few auxiliary features that are only partially integrated, but no critical workflow dead-ends appear for the primary data-research use cases.