action1-mcp-server

Search endpoints (client-side substring filter, cursor-paginated)

action1_search_endpoints

Read-onlyIdempotent

Search endpoints by case-insensitive substring across hostname, user, OS, or status fields, with pagination and field/projection controls to find matching devices.

Instructions

Case-insensitive substring search restricted to hostname, user, OS and status fields. Walks the endpoint list page by page and matches client-side.

Input Schema

Name	Required	Description
`limit`	No	Max items.
`query`	Yes	Substring (case-insensitive).
`cursor`	No	Pagination cursor.
`fields`	No	Restrict matching to these fields.
`org_id`	No	Org UUID.
`projection`	No	Per-endpoint projection.
`response_format`	No	Output format. Default markdown.

Output Schema

Name	Required	Description	Default
`note`	No
`count`	Yes
`items`	Yes
`total`	No
`has_more`	No
`next_cursor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.6.0Oct 26, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +{}
```
addedOutput schema / properties / items / items / propertyNames
```
Added value: +{
+  "type": "string"
+}
```

First observedv0.5.0Jun 27, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly/idempotent/non-destructive, so the description earns its credit by disclosing the implementation trait: matching is done client-side while walking pages via cursor. That tells an agent results depend on full traversal and can be slow on large estates, which is genuinely useful. Output format/projection behavior is left to the schema and output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, with the matching semantics front-loaded and the traversal mechanism second. Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description only needs to convey matching semantics and traversal cost, and it does both. A note on the default field set (what happens when 'fields' is omitted) would close the last gap for a 7-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline applies. The description's enumeration of hostname/user/OS/status mirrors the 'fields' enum without adding defaults, precedence, or how an omitted 'fields' behaves, so it adds little beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('substring search ... endpoint list') plus the searched fields, which separates it from a plain list operation. It never names the sibling it competes with (action1_list_endpoints, action1_search), so differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'case-insensitive substring' framing implies the tool is for text matching rather than browsing or filtered listing, which is a usable signal. There is no explicit when-to-use/when-not or pointer to action1_list_endpoints for unfiltered enumeration or action1_search for other resources.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server