io.github.koten-ai/zeus-dev-helper

Official

Overview Schema Source Related Servers Discussions Admin

recommend_surface

Read-onlyIdempotent

Recommends which website input surface to use—direct list, chips, typeahead, paging, detail, or One chat—based on intent and URL/scope counts.

Instructions

Name each website input. One box still returns one surface. Does not call Zeus.

A website (intent=nl_question) returns inputs: Direct list, chips, typeahead, paging, and detail, plus a One chat question box. url_count, scope_count, or report_wait_s of 20 seconds or more is a Job hint. The tool does not write jobs.host_url. Zero counts mean one URL and one scope.

Input Schema

Name	Required	Description	Default
`qps`	No
`page`	No
`intent`	Yes
`needs_llm`	No
`url_count`	No
`scope_count`	No
`report_wait_s`	No
`settings_mode`	No
`page_interaction`	No
`source_type_count`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.7.10Oct 30, 2026

addedInput schema / properties / page

Added value: +{
+  "default": "",
+  "title": "Page",
+  "type": "string"
+}

addedInput schema / properties / page_interaction

Added value: +{
+  "default": false,
+  "title": "Page Interaction",
+  "type": "boolean"
+}

addedInput schema / properties / report_wait_s

Added value: +{
+  "default": 0,
+  "title": "Report Wait S",
+  "type": "number"
+}

addedInput schema / properties / scope_count

Added value: +{
+  "default": 0,
+  "title": "Scope Count",
+  "type": "integer"
+}

addedInput schema / properties / settings_mode

Added value: +{
+  "default": "",
+  "title": "Settings Mode",
+  "type": "string"
+}

addedInput schema / properties / source_type_count

Added value: +{
+  "default": 0,
+  "title": "Source Type Count",
+  "type": "integer"
+}

addedInput schema / properties / url_count

Added value: +{
+  "default": 0,
+  "title": "Url Count",
+  "type": "integer"
+}

First observedv0.7.3Sep 22, 2026

TDQS

C2.3/5.0

Behavior3/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive tool. The description adds useful behavioral boundaries, notably "Does not call Zeus" and "does not write jobs.host_url," plus hints about Job-like thresholds, though the disclosure remains terse and partly opaque.

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

Conciseness3/5

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

The text is short and has no obvious padding, but it is fragmented and poorly front-loaded. The opening sentences are confusing rather than efficiently orienting the agent.

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

Completeness2/5

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

The tool has 10 parameters, no schema descriptions, and an output schema, but the description only covers a few parameters and a couple of behavioral constraints. An agent would still lack enough information to confidently supply most inputs or understand the recommendation logic.

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

Parameters2/5

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 all 10 parameters. It only clarifies intent=nl_question and gives partial meaning for url_count, scope_count, report_wait_s, and zero-count defaults, leaving qps, page, needs_llm, settings_mode, page_interaction, and source_type_count unexplained.

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

Purpose2/5

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

The description never clearly states that the tool recommends a UI surface. Phrases like "Name each website input" and "One box still returns one surface" are cryptic, and the purpose must be inferred from mentions of returned inputs such as Direct list, chips, and typeahead.

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

Usage Guidelines2/5

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

It mentions a website intent=nl_question case but gives no clear when-to-use guidance relative to alternatives. There is no explicit exclusion or routing advice involving sibling tools such as next_step, explain_scope, or website_green.

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

Deploy Server