docs

Describe the page’s adaptive dimensions

describe_page_dimensions

Read-only

Describe the adaptive dimensions of this site's pages: each named layout regime, the states it can occupy, and the signal and thresholds it is carved from. These are the same boundary definitions that emit the page's @container CSS, so this is the page's real state space rather than a description of it. Read-only — no tool here changes the page. Caveat: each dimension's current field is an SSR-time fallback (always the first state), NOT the requesting browser's live state — this manifest is compiled once, server-side, with no viewport to read. HOW to find the live state differs per dimension — some have a data-czap-state DOM attribute to read, some do not and must be derived from viewport width against the stated thresholds instead — so read each dimension's own description rather than assuming one mechanism for all of them.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
`dimensions`	Yes	Dimension name -> { states, current, exclusive, description }. `current` is an SSR fallback (always states[0]), not the live browser state. How to find the real live state is NOT uniform across dimensions — it is a DOM attribute for some, viewport-derived for others — so each dimension's own `description` states which applies to it; do not assume one mechanism for every dimension.
`systemPrompt`	Yes	Rendered prose naming every dimension and its states.

TDQS

A4.6/5.0

Behavior5/5

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

The description goes far beyond the readOnlyHint annotation by disclosing a critical behavioral caveat: the `current` field is an SSR-time fallback, not the live browser state, and the mechanism to find the live state varies per dimension. This transparency prevents an agent from misinterpreting returned data, which is exactly what behavioral transparency should do.

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

Conciseness4/5

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

The description is longer than the minimal case, but every sentence earns its place: it leads with purpose, then the read-only confirmation, and then the essential caveat about SSR fallback and per-dimension live-state discovery. The structure is logical and front-loaded; while not terse, it is not bloated.

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

Completeness5/5

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

For a tool with no parameters, the description fully explains the output semantics (what is returned), the limitations (SSR fallback), and how to correctly interpret the data (read each dimension's description). With an output schema presumably defining structure, nothing is missing for an agent to call and use this correctly.

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

Parameters4/5

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

The tool has zero parameters, so there is nothing for the description to add beyond the schema (which is empty). The baseline of 4 for 0-param tools is appropriate because the schema covers everything (100% coverage trivially) and no parameter guidance is needed.

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

Purpose5/5

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

The description states a specific verb ('describe'), a resource ('adaptive dimensions of this site's pages'), and details the content (each layout regime, states, signal, thresholds). It clearly distinguishes itself from siblings, which are all about docs/products (get_doc, list_products, etc.), so an agent would never confuse this tool with them.

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

Usage Guidelines4/5

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

The description provides clear context for what the tool is for, but does not explicitly state when to use it vs alternatives. However, since no sibling tools perform a similar function, omitting explicit alternatives is acceptable. The read-only statement helps signal it's for inspection, not modification.

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

All docs tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation4/5

Each tool has a clearly distinct role: list_products discovers products, search_docs finds pages, get_doc fetches a single page, and get_llms_full returns the whole corpus. There is minor potential for confusion between get_doc and get_llms_full about which to use, but the descriptions explicitly address this.

Naming Consistency4/5

The verb_noun pattern is consistent across all tools: list_products, search_docs, get_doc, get_llms_full. The only slight deviation is the cryptic 'get_llms_full' name, which is not immediately clear, but the pattern itself is consistent.

Tool Count5/5

Four tools is a well-scoped count for a documentation search/retrieval server. Each tool serves a necessary function in the discovery and retrieval workflow, and none feel redundant.

Completeness5/5

The surface covers the full discovery-to-retrieval flow: discovering products, searching all docs, fetching a specific page, and retrieving the entire corpus. There are no obvious gaps for documentation browsing needs.

Resources

Need Help?