tela

Overview Schema Source Related Servers Discussions Admin

Add comment

add_comment

Posts comments on wiki pages, anchoring root feedback to plain-text passages and replying inside existing threads; idempotency keys prevent duplicate retries.

Instructions

Comment on a page (editor+). Omit parent_id for a ROOT comment: it needs an anchor, a {prefix, exact, suffix} text triplet that pins it to a passage so it survives edits to the page. Pass parent_id to REPLY inside an existing thread (no anchor; replying to a reply is rejected) — that is how you answer a person's comment, rather than posting a second root beside theirs. ANCHOR TEXT IS THE PAGE'S PLAIN TEXT, NOT ITS MARKDOWN: inline markers are stripped (**ship it** is anchored as ship it), blocks are joined by single newlines, and prefix/suffix hold at most 32 characters of surrounding context. Quote the passage as a reader sees it, not as get_page returns it. Pass idempotency_key to make retries safe (a repeat returns the original comment instead of posting a duplicate). Use for feedback ON page content; to report problems with tela itself use submit_feedback.

Input Schema

Name	Required	Description
`body`	Yes	comment text (1-10000 chars)
`anchor`	No	text-quote anchor locating the comment in the page's PLAIN TEXT (markdown markers stripped); required for a root comment, omit when replying
`page_id`	Yes	page to comment on
`parent_id`	No	id of the root comment to reply to; omit to start a new thread
`idempotency_key`	No	optional client-generated key; a retry with the same key returns the original result instead of posting a duplicate comment (safe retries after a dropped connection)

Output Schema

Name	Required	Description	Default
`comment`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.11.0Oct 15, 2026

changedInput schema / properties / anchor / description

Previous value: -"text-quote anchor locating the comment in the body"New value: +"text-quote anchor locating the comment in the page's PLAIN TEXT (markdown markers stripped); required for a root comment, omit when replying"

changedInput schema / properties / anchor / type

Previous value: -"object"New value: +[
+  "null",
+  "object"
+]

addedInput schema / properties / parent_id

Added value: +{
+  "description": "id of the root comment to reply to; omit to start a new thread",
+  "type": [
+    "null",
+    "integer"
+  ]
+}

changedInput schema / required

Previous value: -[
-  "page_id",
-  "anchor",
-  "body"
-]New value: +[
+  "page_id",
+  "body"
+]

First observedv0.1.0Jul 5, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and the description adds context those hints cannot convey: the editor+ permission requirement, the root-vs-reply precondition on anchor, the rejection of replies-to-replies, and idempotency_key semantics for safe retries (a repeat returns the original comment rather than duplicating). No contradictions 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.

Conciseness4/5

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

Dense but front-loaded: the root-vs-reply rule leads, then anchor mechanics, then idempotency, then the sibling routing. Every sentence carries operational information, though the parenthetical-heavy run-on style makes it a wall of text rather than cleanly chunked guidance.

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 5-parameter mutation tool with an output schema (so return values need no explanation) and annotations covering the safety profile, the description covers the remaining gaps: permissions, the anchor precondition for roots, the reply precondition and its rejection case, and retry safety. Nothing needed to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not carry: anchor text must be the page's plain text with markdown markers stripped (`**ship it**` -> `ship it`), blocks joined by single newlines, and prefix/suffix limited to at most 32 characters of context. It also explains the retry behavior of idempotency_key beyond the schema's brief note.

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?

States a specific verb+resource ('Comment on a page') and immediately scopes it with a permission level ('editor+'). It distinguishes itself from siblings by explicitly routing 'problems with tela itself' to submit_feedback and by separating root comments from replies, so an agent can tell it apart from list_comments and update_comment.

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

Usage Guidelines5/5

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

Gives explicit branching rules: omit parent_id for a root comment (which then requires an anchor), pass parent_id to reply inside a thread, and use submit_feedback for product problems. It also names a rejected case ('replying to a reply is rejected'), which is exactly the kind of exclusion that prevents misinvocation.

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