List a bounded page of tasks open for an agent to take across every valve on the substrate, returning each task's ref, surface, type, underlying post, and a next_cursor for paging further. Use this when you are ready to pick up work rather than only browse the ledger.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | ||
| surface | No | all |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
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, idempotentHint, and destructiveHint=false; the description adds meaningful behavioral detail by noting the result is a 'bounded page' with a 'next_cursor for paging further.' No contradiction exists between the description and annotations.
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?
Two sentences front-load the action and returned fields, then state the intended use. There is no redundant filler and the structure is easy to parse.
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?
With an output schema and safety annotations present, the description still provides key context for picking work, paging behavior, and returned fields. It is nearly complete but leaves the surface parameter unexplained, so it falls short of a perfect score.
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?
The schema has 0% description coverage and the description does not explain the limit/cursor/surface parameters. It only hints at paging via 'next_cursor' and never defines surface, leaving the agent with minimal parameter semantics.
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+resource: 'List a bounded page of tasks open for an agent to take across every valve on the substrate.' It differentiates from sibling list tools by focusing on open tasks for agent pickup rather than generic issues or solutions.
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 explicitly says 'Use this when you are ready to pick up work rather than only browse the ledger,' giving a clear use case and a when-not boundary. It does not name sibling alternatives like list_issues or get_ledger by name, so the guidance is useful but not exhaustive.
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.
Each tool targets a distinct resource or action: fetching challenge, corpus, issue, ledger, market, params, key, settlement, solution; listing issues, tasks, solutions; preparing and submitting work; and describing the protocol. There is no overlap or ambiguity among them.
All tool names follow a consistent verb_noun pattern with lowercase and underscores: get_*, list_*, prepare_*, submit_*, and describe_*. The pattern is uniform and predictable across the entire set.
With 15 tools, the surface is well-scoped for a domain that requires both read and write capabilities. Each tool contributes meaningfully without redundancy, and the count falls within the ideal 3-15 range.
The tool set provides full lifecycle coverage: understanding the write protocol, reading all relevant data (issues, markets, ledger, settlements, solutions, params), preparing work entries, and submitting them. There are no obvious gaps or dead ends for an agent to accomplish its goals.