Markdown by mdedit.ai

Add a review comment

add_comment

Add an anchored review comment without directly changing document prose. Accepts natural workspace names and document titles; internal routing identifiers are optional. Returns threadId and targetId for reply_to_thread and resolve_thread.

Input Schema

TableJSON Schema

Name	Required	Description
`body`	Yes
`anchor`	Yes
`targetId`	No
`articleId`	No	Internal document identifier when already available. Omit it when the user referred to the document by title.
`commandId`	No
`workspaceId`	No	Internal workspace identifier when already available. Omit it when the user referred to a workspace by name or has only one workspace.
`articleTitle`	No	Human-visible document title. Prefer this over asking the user for an internal document identifier.
`workspaceName`	No	Human-visible workspace name. Prefer this over asking the user for an internal workspace identifier.

Output Schema

TableJSON Schema

Name	Required	Description
`events`	Yes
`applied`	Yes
`targetId`	Yes	Review target containing the new thread. Pass this exact value with threadId to resolve_thread or reply_to_thread.
`threadId`	Yes	Stable review thread identifier. Pass this exact value with targetId to resolve_thread or reply_to_thread; do not use commandId.
`articleId`	Yes
`commandId`	Yes
`workspaceId`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedAug 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already signal that this is a write operation (readOnlyHint=false) and not destructive. The description adds useful behavior beyond those flags: it explicitly says the tool does not modify document prose, accepts human-friendly names, and returns threadId/targetId for downstream operations. There is no contradiction with the annotations.

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?

The description is two sentences, front-loads the core action and constraint, and every sentence contributes meaningful information. There is no filler or repetition of the tool name or schema fields.

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?

Given the output schema exists, the description does not need to explain return values in depth, yet it still names the key downstream use of threadId and targetId. It covers the main input options and the non-destructive nature of commenting. The only notable omission is explicit guidance about when to choose add_comment over add_suggestion, but the prose-change distinction partially covers that.

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?

The description usefully explains that workspaceName/articleTitle may be used instead of internal identifiers, which complements the schema descriptions for those fields. However, commandId and targetId remain undocumented in both the description and schema, and with 50% schema description coverage the description only partially closes the parameter-meaning gap.

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 opens with a specific verb and object: 'Add an anchored review comment'. It also distinguishes the tool from suggestion tools by saying it does so 'without directly changing document prose', and it states the exact returned identifiers (threadId and targetId), making the purpose unmistakable.

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 gives clear usage context: natural workspace names and document titles are acceptable, internal routing identifiers are optional, and the returned identifiers are meant for reply_to_thread and resolve_thread. It does not explicitly say 'use this instead of add_suggestion', but 'without directly changing document prose' strongly implies the boundary between commenting and suggesting.

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

All Markdown by mdedit.ai 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

A3.6/5.0

Disambiguation4/5

Most tools have clearly distinct purposes across article CRUD, review workflows, publishing, and conversion/export. Minor confusion can arise between convert_document and start_article_export (and their corresponding status checkers), but the descriptions explicitly differentiate arbitrary content conversion from exporting stored documents. The render_article tool's broad contextual wording overlaps conceptually with several actions, though its actual function (opening the reader) is unique.

Naming Consistency5/5

All 22 tool names follow a strict snake_case verb_noun pattern, such as list_articles, accept_suggestion, start_article_export, and unpublish_article. There are no mixed conventions, vague verbs, or camelCase outliers, making the naming highly predictable.

Tool Count3/5

At 22 tools, the server sits above the ideal 3-15 range and feels somewhat heavy for an MCP surface. The inclusion of record_article_app_event, a component-only telemetry tool with no agent-facing value, adds to this heaviness. However, the breadth of the domain—documents, collaboration, publishing, and conversion—largely justifies the count.

Completeness3/5

The tool surface covers article lifecycle, review threads, publishing, export/conversion, and presence well, covering most common workflows. A notable gap is the lack of any delete_article or trash operation, leaving no way to remove documents. Additionally, updates are limited to anchored edits via edit_article, with no direct full-content replacement option.

Resources

Need Help?