Skip to main content
Glama

Analyze Post Attachments

analyze_post_attachments
Read-only

Analyzes the content of attachments (images, videos, audio, PDFs, documents) from posts on the padlet.

  • Purpose: Retrieve and analyze post attachment content so you can describe, summarize, or answer questions about what's in the attachments.

  • What this tool returns: { success: true, analysis: { posts: [{ post_id, attachments: [{ description }] }] } } with a structured analysis grouped by post_id; { success: true, message: "No valid attachments to analyze" } when none of the posts has an attachment it can read; otherwise { success: false, message: "..." }.

Guidance for use:

  • Use this tool when the user asks about the content of images, videos, audio, documents, or other attachments in posts.

  • Identify which posts have attachments before calling. If an EXPLICIT list of post_ids to analyze has been provided to you in the conversation, use those directly. Otherwise, read the padlet first to discover them.

  • A post has an attachment if its "attachment" field contains a URL (not empty, not "poll"). Check BOTH the "attachment" field and "attachment_props" — some posts have a URL in "attachment" but empty "attachment_props".

  • Pass the post_ids of posts whose attachments you want to analyze. The tool will retrieve the attachment URLs automatically.

  • Pass at most 50 post IDs per call. If there are more, prioritize the most relevant posts.

  • Only analyzes attachments the current user has permission to view.

  • Do not use this tool if the user is not asking about attachment content.

  • Results are cached: previously analyzed attachments return cached descriptions without re-analyzing.

  • IMPORTANT: Only pass the query parameter when the user has a specific, targeted question about the attachment content (e.g. "What formula is on slide 3?", "What color is the logo?"). For general requests like "describe the attachments", "what's in the images", or "summarize the content", do NOT pass a query — omit it entirely so the tool returns a comprehensive generic description.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "wall_url": "<wall_url>",
      "post_ids": "<post_ids>"
    },
    "name": "analyze_post_attachments"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoOptional. A specific question about the attachments. Only provide this for targeted questions (e.g. 'What formula is on slide 3?'). Do NOT provide for general descriptions.
post_idsYesIDs of posts whose attachments to analyze, as the padlet's content lists them.
wall_urlYesThe padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link, and not a padlet id: no tool takes a wall_id.
telemetryNoOptional. Padlet records this to improve its tools; it does not change what the tool does.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / telemetry
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional. Padlet records this to improve its tools; it does not change what the tool does.",
      +  "properties": {
      +    "intent": {
      +      "description": "Explain the task and why you are calling this tool. Omit full queries, large inputs, personal information, and secrets.",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / post_ids / description
      Previous value: -"IDs of posts whose attachments to analyze. Get these from get_padlet_content."New value: +"IDs of posts whose attachments to analyze, as the padlet's content lists them."
  3. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / wall_url / description
      Previous value: -"The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link."New value: +"The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link, and not a padlet id: no tool takes a wall_id."
  4. Changed2 schema fields changed
    • addedInput schema / properties / wall_url
      Added value: +{
      +  "description": "The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link.",
      +  "maxLength": 2048,
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "post_ids"
      -]New value: +[
      +  "wall_url",
      +  "post_ids"
      +]
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description goes well beyond by disclosing permission scoping ('Only analyzes attachments the current user has permission to view'), caching ('previously analyzed attachments return cached descriptions without re-analyzing'), and the three success/failure response shapes. This is meaningful context an agent could not derive from 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?

Purpose and return contract are front-loaded, and the bulleted structure makes the decision rules scannable. It is long, and the query-parameter rule is stated twice (in the guidance block and again in the IMPORTANT line, and again in the schema), which is redundant rather than incorrect.

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?

With no output schema, the description correctly takes on the burden of documenting both success and failure payloads. It also covers the pre-call discovery step, the batch limit, permissions, and caching — everything an agent needs to invoke this correctly in one shot.

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?

Schema coverage is 100%, so the baseline is 3; the description still adds value by explaining where post_ids come from (discover via the padlet when no explicit list is given), that the tool resolves attachment URLs itself, and the 50-ID ceiling. The extended query guidance largely duplicates the schema's own query description, which keeps this from a 5.

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 and resource ('Analyzes the content of attachments ... from posts on the padlet') and immediately enumerates the supported media types (images, videos, audio, PDFs, documents), which distinguishes it from post/comment CRUD siblings. The follow-up Purpose bullet restates the goal in outcome terms ('describe, summarize, or answer questions'), removing any ambiguity.

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 when-to-use ('when the user asks about the content of images, videos, audio, documents'), an explicit when-not-to-use ('Do not use this tool if the user is not asking about attachment content'), and preconditions for discovery ('identify which posts have attachments before calling', checking both 'attachment' and 'attachment_props'). It also states the fallback when no explicit post list exists ('read the padlet first') and a hard batching limit of 50 IDs with a prioritization rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.