AI Blocks

Propose experts and a task lead

propose_team

Read-onlyIdempotent

Deterministic relevance and diversity matching from published roles, full palettes and personas. One general coordinator selects a lead for this request; there is no fixed department-head assignment. Review any unmapped catalogue gaps before accepting.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "propose_team"
  }
}

Input Schema

Name	Required	Description	Default
`job`	No
`task`	Yes
`tier`	No
`job_card`	No
`host_capabilities`	No

Output Schema

Name	Required	Description	Default
`schema`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 9, 2026
- removedInput schema / properties / host_capabilities / properties / allow_paid_native
```
Removed value: -{
-  "type": "boolean"
-}
```
- removedInput schema / properties / host_capabilities / properties / native_tools
```
Removed value: -{
-  "items": {
-    "type": "object"
-  },
-  "maxItems": 30,
-  "type": "array"
-}
```
Changed2 schema fields changedNov 8, 2026
- addedInput schema / properties / host_capabilities / properties / allow_paid_native
```
Added value: +{
+  "type": "boolean"
+}
```
- addedInput schema / properties / host_capabilities / properties / native_tools
```
Added value: +{
+  "items": {
+    "type": "object"
+  },
+  "maxItems": 30,
+  "type": "array"
+}
```
AddedNov 8, 2026

TDQS

C2.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine context beyond that: matching is deterministic, a single general coordinator picks the lead, there is no fixed department-head assignment, and gaps should be reviewed before accepting. It still says nothing about what the proposal contains or how gaps surface.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no obvious padding, but the lead sentence is abstract jargon ('relevance and diversity matching from published roles, full palettes and personas') that delays the concrete point about selecting a lead. Structure is acceptable but not front-loaded with the actionable meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be described, but the input side is a major hole: five parameters at 0% schema coverage, one nested object, and one enum, none of which the description explains. For a planning/selection tool with this much input surface, the description leaves an agent guessing how to populate the request.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, including a nested host_capabilities object with eight sub-fields and an opaque job_card object, so the description carries the full burden. It only alludes vaguely to 'palettes and personas' without mapping anything to task, job, tier, job_card, or host_capabilities, leaving most inputs undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description conveys that this tool matches roles/personas and selects a lead, so the general intent is inferable, but the verb is buried in abstract phrasing ('Deterministic relevance and diversity matching') rather than stating plainly that it proposes a team of experts. It does not distinguish itself from nearby siblings such as find_specialist, prepare_specialist, or plan_workflow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Review any unmapped catalogue gaps before accepting' hints at a propose-then-accept workflow, which is mild usage context. There is no explicit statement of when to call this versus find_specialist/prepare_specialist, and no prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AI Blocks tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?