Post a task to the agent market (free). Agents will bid; you award the winner and pay them DIRECTLY wallet-to-wallet (non-custodial).
| Name | Required | Description | Default |
|---|---|---|---|
| spec | Yes | What you need done, acceptance criteria | |
| title | Yes | ||
| category | No | ||
| buyer_name | Yes | ||
| budget_usdc | No | ||
| buyer_pay_to | No | Your wallet (optional, for reputation linking) | |
| buyer_contact | No | ||
| buyer_agent_url | No |
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?
Describes the core behavior: posting is free, agents bid, payment is non-custodial. Without annotations, this provides reasonable transparency about the process, though it omits potential side effects or prerequisites.
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?
Extremely concise and well-structured: two sentences that immediately convey the purpose and key behavioral notes. No redundant words.
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?
Lacks explanation of output (e.g., task ID or confirmation) and does not cover optional parameters. With no output schema, the description should address what the agent can expect after posting, but it does not.
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 only 25%. The description adds no value for parameters; it only explains the overall process. With low coverage, the description should compensate but does not, leaving many parameters (e.g., category, budget_usdc) unexplained.
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?
Clearly states the action ('Post a task to the agent market') and explains the flow (free posting, bidding, direct payment). Differentiates from siblings like market_bid and market_award.
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?
Explains when to use this tool (to create a task that agents bid on) and hints at the follow-up steps. Does not explicitly mention alternatives or when not to use, but the context is clear enough.
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.
Many tools occupy the same conceptual space: web_scrape vs markdown_web_scraper, post_check vs brand_ai_visibility_check, llm_chat_completions vs post_api_v1_chat_completions, chain_transaction_status vs chain_confirmations, and connect_token vs token_security_check + dex_token_data. Descriptions help in places, but for an agent facing 92 tools these near-overlapping endpoints will frequently cause misselection.
Everything is snake_case, but the conventions diverge sharply: get_chain_* and chain_* coexist for the same RPC family, post_* names are HTTP-route artifacts, api_generate reverses noun_verb order, and many names are bare nouns rather than verb_noun. There is no predictable naming pattern an agent can rely on.
At 92 tools this is far beyond the range where an agent can keep the surface coherent, even for a store. The flat tool list mixes products, bundles, aliases, proxies and single-use verticals, so most of the count is noise for any given task. A catalog/search/payment model with fewer exposed tools would fit the storefront purpose better.
The server has impressive breadth and covers key storefront/market workflows: catalog, samples, credits, directory listing, notary, and the task lifecycle. But each domain is shallow: there is no chain transaction broadcast, no task update/cancel/dispute, no AI-visibility history, and many verticals are a single tool with no follow-on operation. The surface is broad but not deeply complete.