Fetch the raw stored content of a document. Defaults to your own handle and the latest version.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Document name. | |
| handle | No | Owner handle. Defaults to the authenticated user. | |
| version | No | Version number. Defaults to the latest. |
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| appUrl | Yes | ||
| handle | Yes | ||
| rawUrl | Yes | ||
| deleted | No | ||
| snippet | No | ||
| version | Yes | ||
| language | No | ||
| visibility | No | ||
| contentType | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already signals a safe read, and the description adds useful default behavior (own handle, latest version). It does not disclose failure modes, permission requirements, or return format specifics, though the output schema covers the latter. The added context is moderate but not extensive.
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 concise sentences. The primary action and resource are front-loaded, and the default behavior is stated in a separate sentence. No filler or redundant framing exists.
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?
For a simple read-only retrieval tool with an output schema and readOnlyHint annotation, the description covers the essential behavior and defaults. It could add explicit guidance distinguishing it from search_docs, but nothing critical for invoking this tool correctly is missing.
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%, so all three parameters are already documented. The description's mention of defaults ('Defaults to your own handle and the latest version') essentially repeats the schema descriptions, adding no new semantic information beyond what the schema provides.
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 uses a specific verb ('Fetch') and resource ('raw stored content of a document'), making it clear this retrieves document content. It distinguishes itself from sibling tools create_doc and search_docs by focusing on raw content retrieval rather than creation or searching.
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?
Usage is only implied: the tool fetches raw content, so it contrasts with searching or creating, but there is no explicit guidance on when to choose this over search_docs or whether it handles metadata lookups. No alternatives or exclusions are named.
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.
Each tool has a clearly distinct purpose: create, fetch, and search. There is no meaningful overlap between them, since get_doc retrieves exact content while search_docs returns matching document metadata.
All tool names follow a consistent verb_noun pattern: create_doc, get_doc, search_docs. The plural in search_docs is idiomatic and does not create confusion.
Three tools is a focused, appropriate count for this server's scope. Each tool covers a distinct and essential operation without redundancy or bloat.
The core workflow of creating, fetching, and searching is covered, and versioning handles updates. However, there is no delete operation and no way to list all documents without knowing a name, leaving notable lifecycle gaps.