No longer listed separately (still callable): which public agents declare a fit for a task.
Scored across 1 tool
Only one tool exists, so there is no possibility of misselection. Its purpose—preflight filtering of broker candidates—is clearly stated.
The sole tool uses a descriptive snake_case name with a verb/noun-like structure. With only one name, consistency is trivially satisfied.
A single tool is thin for a server named Opportunity Broker. While the preflight operation is substantive, the broader broker concept suggests more operations would be expected.
The tool covers candidate preflight but omits actual brokerage/handoff, status, or feedback operations that a complete broker surface would likely need. Core selection support is present, but the lifecycle is not fully covered.
Use this when choosing which agent to hand a task to ("which of these agents can do X?"). Pass task_class and candidates (A2A agent cards). Returns callable candidates ordered by declared skill match (not a quality ranking), held ones with reasons and a receipt. Free, read-only, no account; inputs must be public and non-personal.
| Name | Required | Description | Default |
|---|---|---|---|
| synthetic | No | Optional: true marks a test call. | |
| candidates | Yes | A2A agent cards as published, or {agent_card, explicit_read_only_consent}. | |
| episode_id | No | Optional: your own id to group related calls. | |
| task_class | No | Optional: short name of the task, e.g. weather_forecast. | |
| continuity_handle | No | Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones. | |
| data_classification | No | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. | PUBLIC |
| independent_operator_id | No | Optional: your operator id (recorded as a claim, not verified). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive, and closed-world. The description adds real value beyond them: it is free, needs no account, inputs must be public and non-personal, and it returns held candidates with reasons plus a receipt. It does not quantify limits or failure modes, which keeps it out of the top band.
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?
Three dense sentences, front-loaded with the triggering situation, then inputs, then return shape. No filler; every clause carries information an agent needs in order to select and call the tool.
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 rich annotations, 100% schema coverage, and no output schema, the description supplies the missing behavioral and return-shape context (ordering semantics, held candidates, receipt, data-sensitivity constraint). Minor gaps remain around limits and error behavior, but nothing essential for correct invocation is absent.
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%, so the baseline is 3. The description names task_class and characterizes candidates as A2A agent cards and adds the public/non-personal input constraint, but adds little syntax or format detail beyond what the schema already documents.
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?
States a specific verb and resource: choosing which agent to hand a task to, given task_class and candidates, returning ordered callable candidates. It even clarifies the semantics ('declared skill match, not a quality ranking'). No sibling tool competes for this function, so no explicit differentiation is needed, but none is offered.
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?
Explicitly says when to use it ('Use this when choosing which agent to hand a task to') and gives the natural-language trigger phrasing ('which of these agents can do X?'). It stops short of naming when-not-to-use conditions or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
preflight_broker_candidates7 fields changedInput schema / properties / candidates / descriptionAdded value: +"A2A agent cards as published, or {agent_card, explicit_read_only_consent}."Input schema / properties / continuity_handle / descriptionAdded value: +"Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones."Input schema / properties / data_classification / descriptionAdded value: +"PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data."Input schema / properties / episode_id / descriptionAdded value: +"Optional: your own id to group related calls."Input schema / properties / independent_operator_id / descriptionAdded value: +"Optional: your operator id (recorded as a claim, not verified)."Input schema / properties / synthetic / descriptionAdded value: +"Optional: true marks a test call."Input schema / properties / task_class / descriptionAdded value: +"Optional: short name of the task, e.g. weather_forecast."preflight_broker_candidates3 fields changedInput schema / examplesAdded value: +[
+ {
+ "candidates": [
+ {
+ "agent_card": {
+ "description": "Public weather forecasts over A2A.",
+ "name": "Open Forecast Agent",
+ "skills": [
+ {
+ "description": "7-day forecast for a named city.",
+ "id": "weather_forecast",
+ "name": "Weather forecast",
+ "tags": [
+ "weather",
+ "forecast"
+ ]
+ }
+ ],
+ "url": "https://forecast.example.com/a2a",
+ "version": "1.2.0"
+ },
+ "explicit_read_only_consent": true
+ },
+ {
+ "agent_card": {
+ "name": "Premium Weather Agent",
+ "security": [
+ {
+ "bearer": []
+ }
+ ],
+ "securitySchemes": {
+ "bearer": {
+ "scheme": "bearer",
+ "type": "http"
+ }
+ },
+ "skills": [
+ {
+ "id": "forecast",
+ "name": "Hyperlocal forecast",
+ "tags": [
+ "weather",
+ "forecast"
+ ]
+ }
+ ],
+ "url": "https://premium-weather.example.com/a2a"
+ },
+ "explicit_read_only_consent": true
+ },
+ {
+ "agent_card": {
+ "name": "FX Agent",
+ "skills": [
+ {
+ "id": "currency_conversion",
+ "name": "Currency conversion",
+ "tags": [
+ "fx",
+ "currency"
+ ]
+ }
+ ],
+ "url": "https://fx.example.com/a2a"
+ }
+ }
+ ],
+ "task_class": "weather_forecast"
+ }
+]Input schema / properties / data_classification / defaultAdded value: +"PUBLIC"Input schema / requiredPrevious value: -[
- "data_classification",
- "task_class",
- "candidates"
-]New value: +[
+ "candidates"
+]preflight_broker_candidatesOpen, unverified census of what AI agents can do; connect and self-report.
Agent-to-agent bounty board: post tasks with stated rewards, fill them, first accepted wins.
Find tools and hosted agents by task, with source documentation and connection requirements.
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
Add one secure layer between your agents and this server.