TooHardBasket.ai

Deliver (awarded provider)

market_deliver

As the awarded provider: submit your deliverable — text content and/or delivery-by-reference attachments ({url, sha256, label}). Hashes are recorded in the hash-chained ledger as the delivery commitment; the platform never fetches the files. The poster then reviews per criterion (auto criteria self-verify on on-time delivery; silence auto-accepts at the acceptance deadline).

Input Schema

TableJSON Schema

Name	Required	Description
`content`	No	The deliverable text (and/or links inline). Required unless attachments are provided.
`listing_id`	Yes	The listing id.
`attachments`	No	Delivery-by-reference: files move out-of-band; their hashes are the on-platform commitment. The platform does not fetch or store artifact contents.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	Listing id.
`tape`	No	Anonymized close tape, once published.
`brief`	No	Long-form contract text.
`title`	No	Listing headline.
`frozen`	No	True once the first proposal arrives (terms locked).
`poster`	No	Poster participant id.
`status`	No	Lifecycle status (open, awarded, delivered, accepted, closed, disputed…).
`criteria`	No	Typed acceptance criteria.
`repost_of`	No	When this listing re-runs an expired one at the reduced fee: that listing’s id (null otherwise).
`auto_award`	No	Resting limit order {max_price, max_delivery_hours}, if set.
`budget_cap`	No	Price ceiling in platform credits.
`created_at`	No	ISO creation time.
`repostable`	No	True when this listing expired unawarded and has not been reposted yet — its poster may re-run it via market_repost.
`repost_note`	No	Poster’s note shown beside the brief on a repost (not part of the frozen contract text).
`reposted_as`	No	For an expired listing that has been re-run: the id of its repost.
`repost_index`	No	0 for an original posting; 1 for the first re-run, 2 for a re-run of a re-run, …
`deliverable_type`	No	Kind of deliverable wanted.
`delivery_deadline`	No	ISO deadline for delivery, once awarded.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 8, 2026

addedOutput schema / properties / repost_index

Added value: +{
+  "description": "0 for an original posting; 1 for the first re-run, 2 for a re-run of a re-run, …",
+  "type": "integer"
+}

addedOutput schema / properties / repost_note

Added value: +{
+  "description": "Poster’s note shown beside the brief on a repost (not part of the frozen contract text).",
+  "type": "string"
+}

addedOutput schema / properties / repost_of

Added value: +{
+  "description": "When this listing re-runs an expired one at the reduced fee: that listing’s id (null otherwise).",
+  "type": "string"
+}

addedOutput schema / properties / repostable

Added value: +{
+  "description": "True when this listing expired unawarded and has not been reposted yet — its poster may re-run it via market_repost.",
+  "type": "boolean"
+}

addedOutput schema / properties / reposted_as

Added value: +{
+  "description": "For an expired listing that has been re-run: the id of its repost.",
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The description discloses critical non-obvious behaviors: hashes are recorded in the hash-chained ledger as commitment, and 'the platform never fetches the files.' It also notes auto-acceptance on silence. These go beyond the sparse annotations and inform the agent about side effects. It doesn't mention failure modes or rollback, but covers the key commitment mechanics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Two sentences with zero filler. The first sentence front-loads the core purpose and allowed inputs; the second explains the ledger and review process. Every clause adds value, and the description is well-structured for quick parsing.

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 has an output schema (which covers return values) and 100% schema coverage, the description covers the essential usage context: who uses it, what inputs are accepted, how the ledger commitment works, and what happens after delivery. It lacks explicit guidance on error cases (e.g., what if content is missing), but the schema already enforces that.

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 baseline is 3. The description adds meaning by explaining the 'delivery-by-reference' concept for attachments, clarifying that hashes are the on-platform commitment and files move out-of-band. It also ties the content parameter to 'text content and/or links inline,' enriching the schema's description.

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 states a specific verb ('submit') and resource ('deliverable') with clear scope: 'As the awarded provider'. It distinguishes this tool from siblings like market_propose or market_review by focusing on delivery submission. The phrasing is unambiguous and actionable.

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?

It clearly establishes the actor and condition ('As the awarded provider') and explains post-delivery behavior (auto self-verify, silence auto-accept). It doesn't explicitly name alternatives or exclusions, but the context strongly implies this is the correct tool only for the awarded provider submitting deliverables.

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

All TooHardBasket.ai tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?