Resolve a real-world capability request. Search the official MCP Registry, actively validate public candidate MCP tool surfaces, then fall back to live web search when native coverage is weak or absent. Weak Registry matches never suppress capability-gap telemetry.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | What the principal agent wants done | |
| budget | No | ||
| currency | No | ||
| deadline | No | ||
| location | No | ||
| telemetry | No | aggregate_only | |
| categoryHint | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the transparency burden. It discloses the search-and-fallback strategy and the telemetry behavior for weak Registry matches, but omits side effects, return values, or error paths. These omissions prevent a higher score.
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 three sentences that front-load the purpose, then detail the method, and end with a behavioral caveat. It is economical and avoids filler, though a more structured format could improve scannability.
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 7 parameters and no output schema, the description is too high-level. It doesn't explain how parameters influence resolution, what the return format is, or what constitutes a successful result, leaving significant gaps for an agent.
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 coverage is only 14%, with only 'task' described. The description adds no explanation for budget, currency, deadline, location, telemetry, or categoryHint, leaving their semantics entirely to the schema. It fails to compensate for the low coverage.
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 tool resolves a real-world capability request and outlines the resolution process (registry search, validation, web fallback), which distinguishes it from siblings. However, it doesn't explicitly contrast with report_outcome or submit_mandate, so it doesn't reach the top tier.
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 use for capability requests and mentions a fallback condition (weak/absent native coverage), but it doesn't explicitly say when to use this tool over siblings or provide exclusions/prerequisites. Usage guidance is present but implicit.
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 serves a clearly distinct function: resolve performs the search/validation, submit_mandate records intent for future fulfillment, and report_outcome provides feedback on resolver performance. No two tools appear to overlap in purpose.
Two tools follow the verb_noun pattern (report_outcome, submit_mandate), while 'resolve' is a lone verb. All names use lowercase and underscores, so the style is consistent, but the missing noun in 'resolve' is a minor deviation.
Three tools is slightly on the lean side for a service that claims to handle real-world capability requests, but the set covers the core actions of resolve, submit, and report. It is within the reasonable range and each tool earns its place.
The tools form a coherent loop for capability resolution and feedback. A minor gap is the lack of a way to query outstanding mandates or inspect historical outcomes, but the core workflow appears complete for its stated purpose.