Resolve a reputation stake (success: recover + bonus, failure: lose stake)
| Name | Required | Description | Default |
|---|---|---|---|
| outcome | Yes | The outcome of the staked task | |
| evidence | No | Optional evidence or notes about the outcome | |
| stake_id | Yes | The stake ID to resolve | |
| resolver_agent_id | No | Agent ID resolving the stake (for authorization - staking agent can only mark failure, requester can mark success) |
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 provided, the description carries the full burden of disclosure. It does reveal the core behavioral outcomes (recover+bonus or lose stake), but it omits other important traits such as authorization constraints, finality, impact on balances or reputation scores, and whether the operation is reversible. This is somewhat thin for a financial/reputation mutation tool.
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 a single, front-loaded sentence with no redundancy. It conveys the essential purpose and outcome in a compact format, making it easy for an agent to parse quickly.
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?
For a tool with 4 parameters and no output schema, the description provides the core purpose and outcome, but lacks context on prerequisites (e.g., stake must exist and be pending), return values, and side effects beyond the stake itself. It is adequate but has gaps that could lead to incorrect usage without additional information.
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 covers all four parameters with descriptions, so the baseline is 3. The description adds value by explicitly mapping the 'outcome' parameter to its implications: success recovers stake plus bonus, failure loses the stake. This goes beyond the enum labels and enriches the 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 the action ('Resolve a reputation stake') and specifies the two possible outcomes with their consequences ('success: recover + bonus, failure: lose stake'). This distinguishes it from sibling tools like create_stake and get_stakes, which serve different purposes.
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 the tool is used to resolve an existing stake, but it does not explicitly state when to use it versus alternatives, nor does it mention any prerequisites or exclusions. The context is clear for a user familiar with staking workflows, but less explicit for an agent needing decision guidance.
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.
Most tools target distinct resources and actions. The only potential confusion is between approve_job and complete_deal, both releasing payments, but descriptions clearly differentiate job vs deal contexts. Overall, tools are well-separated.
Almost all tools follow a consistent verb_noun pattern (create_, get_, list_, etc.). The only outlier is network_stats, which lacks a verb, but this is a minor deviation from an otherwise uniform convention.
With 29 tools, the set exceeds the 25-tool threshold for a well-scoped server. While the platform covers many domains (jobs, payments, trust, identity, campaigns, tickets), the high count feels heavy and could benefit from consolidation or clearer separation into sub-modules.
Core job and stake lifecycles are fully covered, but tickets and campaigns only support create/list/get with no update, delete, or close operations. Payment also lacks a direct send/unified transfer option. These gaps are notable but workarounds exist via deals and top-up links.