seneschal_builder_leaderboardSlot-by-slot ground-truth share of Ethereum mainnet block builders observed by Seneschal's shadow recorder, with total MEV captured per builder in the window. Cached for 60s.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Top-N builders to return. Default 20. | |
| window | No | Lookback window. Default 24h. |
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?
With no annotations, the description carries the burden of behavioral disclosure. It transparently notes the 60-second cache and explains data comes from Seneschal's shadow recorder, which conveys read-only observational behavior. It could further clarify output ordering or exact share format, but the provided traits are valuable.
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 tight sentences that front-load the core purpose and add a critical behavioral note about caching. Every word contributes value, with no filler or repetition of schema information.
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?
Despite having no output schema, the description conveys the key result fields (share and MEV per builder) and the window context. It could explicitly state that results are sorted/ranked by share or limit behavior, but given the parameter schema already covers defaults and enums, the description is sufficiently complete for a read-only leaderboard tool.
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 window parameters already described in the schema. The tool description adds minimal context (the word 'window' aligns with the parameter) but does not supplement parameter semantics beyond what the schema provides, so the baseline of 3 applies.
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 specifies a resource (Ethereum mainnet block builders) and the exact metrics provided (slot-by-slot ground-truth share and total MEV captured). It distinguishes this tool from siblings by highlighting Seneschal's shadow recorder and the window scope, making it unique among builder-related tools.
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 description implies when to use the tool (to get authoritative builder share data over a window) but does not explicitly state alternatives or exclusions. The caching note suggests data is not real-time, but no sibling tools are mentioned for comparison.
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.
Tools are grouped by domain (board, private_watch, zecmon) with clear lifecycle separation, but seneschal_list_at_risk_borrowers and seneschal_list_borrowers overlap heavily, and the USDC vs crypto variants of private_watch_create/topup could be confused without careful reading.
Most tools follow a seneschal_<domain>_<action> pattern, but verb/noun order varies (get_borrower vs list_borrowers vs board_list) and outliers like seneschal_health and seneschal_q break the pattern.
At 35 tools, the server is definitely heavy, but it covers multiple distinct domains (DeFi data, privacy-chain monitoring, notice boards, payments), so the count is at the high end of reasonable rather than absurdly bloated.
Core workflows are well covered: borrower discovery/analysis, liquidations, private watch lifecycle, Zcash scanning lifecycle, board operations, and checkout invoices. Minor gaps like board deletion or watch cancellation exist but are workaround-able.