get_articleGet the article content as markdown. Screenshots appear as <SCREENSHOT {id}> placeholders, and things markdown can't show (an embedded video, a pasted image) as <EMBED {id}> placeholders. Returns the markdown text, a list of screenshot IDs and the article_version to pass to update_article.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project ID |
Changes observed during successful MCP inspections.
Input schema / properties / contextRemoved value: -{
- "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
- "type": "string"
-}Input schema / properties / conversation_idRemoved value: -{
- "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
- "type": "string"
-}Input schema / properties / llm_modelRemoved value: -{
- "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
- "type": "string"
-}Input schema / requiredPrevious value: -[
- "project_id",
- "context",
- "llm_model"
-]New value: +[
+ "project_id"
+]Input schema / properties / contextAdded value: +{
+ "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+ "type": "string"
+}Input schema / properties / conversation_idAdded value: +{
+ "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
+ "type": "string"
+}Input schema / properties / llm_modelAdded value: +{
+ "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "project_id"
-]New value: +[
+ "project_id",
+ "context",
+ "llm_model"
+]Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/non-destructive, so the safety profile is covered. The description goes beyond that by disclosing the placeholder conventions (<SCREENSHOT {id}>, <EMBED {id}>) that will appear in the returned markdown and by naming the returned fields — genuinely useful behavioral context that annotations cannot provide.
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?
Three sentences, front-loaded with the core action and output format; each sentence adds distinct information (format, placeholders, return fields). Slightly dense with two placeholder idioms in one sentence, but no wasted text.
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?
With no output schema, the description correctly takes on the burden of describing the return value (markdown text, screenshot ID list, article_version), which is the key missing piece an agent would otherwise lack. It is complete for a simple one-parameter read tool, though it could note whether screenshot IDs map to a companion fetch tool.
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% for the single parameter (project_id), so the schema already carries the parameter documentation. The description adds nothing about the parameter, which is acceptable at baseline but no better.
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?
States a specific verb and resource ('Get the article content as markdown') and immediately explains the representation the agent will receive. It doesn't explicitly differentiate itself from siblings like get_embed or get_clueprint, though 'article content' vs. embed content is reasonably distinct.
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 implied by the mention that the returned article_version is 'to pass to update_article', which hints at the read-modify-write workflow. However, there is no explicit statement of when to call this versus other content-fetching siblings, nor any prerequisite or exclusion guidance.
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.