list_memoryList the durable facts & preferences saved in this workspace’s Memory (what the studio remembers about the brand, audience, taste, and do/don’t rules) — the same Memory the web app shows. These shape every future ad. Read-only, free.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max items (default 50, max 200) | |
| category | No | filter to one bucket (Brand/Audience/Taste/Do/Don’t/Preference) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the description need not restate safety; 'Read-only, free' reinforces this without contradiction. The description adds valuable behavioral context beyond annotations: facts are 'durable,' scoped to 'this workspace,' and identical to what the web app displays, clarifying the source of truth and persistence semantics.
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?
The description is two sentences with no filler. It front-loads the action and resource ('List the durable facts & preferences saved in this workspace's Memory'), then adds purpose and safety context. Every clause earns its place, and the length is appropriate for a simple tool.
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?
For a simple read-only tool with two optional parameters and no output schema, the description is largely complete: it explains what is listed, the scope, the relationship to the web app, and the relevance to future ads. It could explicitly note that the result is a list of individual memory entries or mention the 'Preference' category, but these are minor gaps given the explicit verb and schema.
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%, with both limit and category fully described in the input schema. The description itself does not add parameter-level semantics, but that is acceptable because the schema already carries the burden. The category values in the schema align with the categories named in the description, which helps but is not additional parameter guidance.
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?
The description clearly states a specific verb and resource: list the durable facts and preferences saved in the workspace's Memory. It also distinguishes the content scope (brand, audience, taste, do/don't rules) and links it to the web app, making the tool's function unmistakable. However, it does not explicitly differentiate it from related sibling tools like remember, forget, or tidy_memory.
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?
The phrase 'These shape every future ad' implies this tool is useful when an agent needs to know the studio's stored memory before making ad-related decisions. It also signals the tool is safe by saying 'Read-only, free.' However, there is no explicit guidance about when to use this instead of remembering, forgetting, or tidying memory, nor any exclusion conditions.
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.
The descriptions are exceptionally detailed and cross-reference one another (e.g. post_edit vs finish_video vs edit_video), which genuinely helps, but 168 tools still contain tight clusters—video creation/editing, scheduling, and post-publishing—where misselection is easy. Many tools also reference hidden companions not in the visible set, adding ambiguity.
The overwhelming majority follow a clear verb_noun snake_case convention (post_to_x, search_x, list_x, create_x, update_x). Minor deviations like store_get, billing_status, error_detail, and the hermoso_ prefix break the pattern slightly but do not obscure it.
At 168 tools this is far beyond the 50+ threshold, and regardless of how broad the platform's purpose is, the sheer number makes the set hard to navigate. The server mitigates with groups and find_tools/call_tool, but the count itself is extreme.
The set covers a full marketing lifecycle—research, planning, creation, publishing, scheduling, measurement, billing, and file management—with no major workflow gaps. Some referenced tools like list_shopify_products and manage_meta_post are not in the visible list, but find_tools and call_tool are explicitly designed to close that gap.