Skip to main content
Glama

Check a section visually (contact sheets)

inspo_review

Returns numbered contact sheets of a section’s references so you can visually verify each matches the section and identify wrong IDs for removal before refilling via harvest.

Instructions

Returns numbered contact sheets of a section's references so you can SEE them and verify each one really is that section (a footer is a footer, testimonials are testimonials — not a whole landing page, an app screen or an ad). Then inspo_remove the wrong ids (they are blocked for good) and run inspo_harvest again to refill. By default returns references not reviewed yet, 24 per call (2 sheets); call again for the next batch.

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": {
      "section": "<section>"
    },
    "name": "inspo_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoInclude already-reviewed items.
limitNoDefault 24.
sectionYes
sessionNoSession id. Defaults to the most recent session in this project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the disclosure burden and does well: it reveals the return medium (images/contact sheets), the default filter (unreviewed only), the page size (24, 2 sheets, limit up to 48), and the irreversible consequence of the downstream step ("they are blocked for good"). It does not state that the call itself is non-mutating or mention cost/latency of generating visual sheets, which for an image-returning tool would be worth one more clause.

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?

Front-loaded with what is returned and why, then the follow-up workflow, then the paging defaults — a sensible order. The middle parenthetical example list is long and slightly run-on, but it earns its place by preventing the exact misuse the tool exists to catch.

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?

No output schema exists, so the description must explain the return value and it does (numbered contact sheets, 2 per call). The one residual gap is that it never makes explicit that the printed numbers are the ids to pass to inspo_remove, which is the critical bridge for the described follow-up workflow.

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 75%, so the schema already handles most parameters; the description still adds real meaning by explaining the default review filter that maps to `all` ("references not reviewed yet") and by restating the `limit` default as 24 with the 2-sheet framing. It says little about `session` or about allowed `section` values beyond "a section's references", leaving those to the schema and enum.

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 output ("Returns numbered contact sheets of a section's references") plus the reason for the visual format — verifying that each reference actually belongs to the named section, with concrete contrast examples ("a footer is a footer... not a whole landing page, an app screen or an ad"). This is clearly distinguishable from inspo_harvest (fetching) and inspo_remove (deleting), which are named as the surrounding steps.

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 the full operating loop: call this to visually verify, then inspo_remove the wrong ids, then inspo_harvest again to refill. It also states the batching contract — by default only unreviewed references, 24 per call (2 sheets), call again for the next batch — so an agent knows both when to call it and how to iterate.

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