Skip to main content
Glama

Heista

by co.heista

Save Asset

save_asset

Persist a new saved asset to the workspace. category MUST be one of STRATEGY, IDEAS, COPY, VISUALS, MOTION (BRIEFS lives in creator_briefs and is not saveable through this tool). format MUST match the per-category enum (see input description). title is required. body_text + metadata are recommended. Source attribution (heist_slug, session_id, pattern) lets the user trace the save back to its origin in the /assets timeline. Brand and brief_id link the save to a PowerSource for downstream filtering. Returns the inserted asset row.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoFree-form tags for filtering and search.
titleYesCard title — what shows in /assets.
formatYesPer-category format. STRATEGY: positioning, brand-platform, campaign-strategy, strategic-doc. IDEAS: hook, concept, big-idea, territory. COPY: ad-script, hook, campaign-copy. VISUALS: static-ad, product, lifestyle, hero, moodboard, packaging, logo. MOTION: talking-head, b-roll, product-motion, brand-lifestyle.
sourceYesSave attribution.
brand_idNoBrand the asset is for. Resolved from brief_id when omitted.
brief_idNoPowerSource (brief) the asset was generated against.
categoryYesOne of STRATEGY, IDEAS, COPY, VISUALS, MOTION. BRIEFS is not accepted — briefs live in the creator_briefs table via the briefs API.
metadataNoType-specific bag — duration, image dimensions, model used, beat count, etc.
body_htmlNoRich-text body where the asset carries structured markup.
body_textNoPrimary text body for STRATEGY / IDEAS / COPY saves.
media_urlNoDirect media URL for VISUALS / MOTION (external host).
parent_idNoParent asset id for variations grouped under one save set.
thumb_urlNoCard thumbnail URL.
media_storage_pathNoStorage path inside the private `saved-assets` bucket. Obtain via the /api/saved-assets/upload-url route (REST only; no MCP upload tool yet).

TDQS

A4.4/5.0
Behavior4/5

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

Annotations indicate readOnlyHint=false, so mutation is expected. The description confirms by saying 'persist' and 'create'. It adds context about source attribution for tracing and mention of downstream filtering. It does not elaborate on idempotency or rate limits, but the annotations already cover the safety profile. No contradiction.

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?

The description is a single paragraph of multiple sentences, front-loaded with the main action. It is relatively concise given 14 parameters, though could benefit from bullet points for readability. No wasted words.

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 tool's complexity (14 params, nested objects, no output schema), the description covers the key aspects: purpose, required fields, constraints, source attribution, and return value. Optional fields are left to the schema, which is acceptable. The return statement 'Returns the inserted asset row' is sufficient.

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 description coverage is 100%, yet the description adds significant meaning: explains category restriction, format per-category, title requirement, recommendation for body_text and metadata, source attribution purpose, and brand/brief_id linking. This goes well beyond the schema descriptions.

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 clearly states it persists a new saved asset. It specifies the category enum, format requirements, and distinguishes from BRIEFS which are not saveable here. It contrasts with sibling tools like delete_saved_asset and get_saved_asset.

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 provides explicit guidance on when to use: category must be one of the listed ones, format must match per-category enum, title is required. It states that BRIEFS are not saveable here, and recommends body_text and metadata. It does not explicitly compare with other sibling tools like add_brand_asset, but the constraints are well articulated.

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

All Heista toolsInspect
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

A3.7/5.0
Disambiguation4/5

Despite the high tool count, most tools have distinct purposes with thorough descriptions that specify when to use each. Some overlap exists among creative direction tools (call_creative_worlds vs chat_with_creative_worlds), but the descriptions clarify usage patterns.

Naming Consistency3/5

Naming conventions are inconsistent overall: some follow verb_noun (create_powersource_url, decode_ad), others use noun_verb or compound names (adformula_intelligence, fleet_analytics_overview). However, subgroups like dispatch_* and list_*_presets maintain internal consistency.

Tool Count2/5

112 tools is far beyond the typical 3-15 range for well-scoped servers. While the server covers a broad domain, the sheer number likely overwhelms agents and suggests insufficient consolidation of related operations.

Completeness4/5

The tool set covers core creative intelligence workflows: brand analysis, ad decoding, script generation, creative direction, and research. Minor gaps exist (e.g., no social media publishing tools), but the main use cases are well-supported.

Resources