agent-guild

guild_preflight_outcome

After a guild_preflight verdict, tell the Guild what you did and what happened (AGPO-1). Free, no key, optional.

action: called | delegated | declined | skipped. observed: success | failure | unknown (unknown when you did not call). detail: what failed — by your call, or by your OWN direct check when you did not call (timeout | unreachable | http_5xx | protocol_error | payment_mismatch | card_unavailable | signature_invalid | identity_mismatch | wrong_result | other | http_4xx). AG's warning is credited only when this names the same check AG failed. baseline_direct_check: success | failure | not_run — whether you checked the endpoint yourself without the Guild. Without it a skip is recorded as counterfactual_unobserved, never as a benefit. decision_basis: ag_evidence | own_check | both | other | unknown — what actually drove your decision. Recorded as your claim. AG is credited only when its warning was right AND you say it drove the decision. api_key (optional): the same registered key you presented to guild_preflight, so the two records join under one identity (identity continuity only — not a claim of independence). Invalid keys are refused.

Benefits and mistakes are measured with equal weight; see GET /preflight/outcomes for the public classification rules.

Input Schema

Name	Required	Default
`action`	Yes
`detail`	No	not_applicable
`api_key`	No
`observed`	No	unknown
`overhead_ms`	No
`preflight_id`	Yes
`decision_basis`	No	unknown
`baseline_direct_check`	No	not_run

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026
- addedInput schema / properties / api_key
```
Added value: +{
+  "default": "",
+  "type": "string"
+}
```
AddedSep 22, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the auth requirement (free, no key; invalid keys refused), the crediting rules ('AG's warning is credited only when this names the same check AG failed'), how a skip without a baseline is classified (counterfactual_unobserved), and that decision_basis is recorded as the caller's claim. It does not explain rate limits or the return payload, but the behavioral contract is well covered.

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

Conciseness4/5

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

The first sentence is front-loaded and states the tool's role, then parameters are laid out as a clean field-by-field list. It is somewhat long and prose-heavy in the detail/crediting lines, but no sentence is pure filler.

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

Completeness4/5

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 need not be explained. For an 8-parameter reporting tool the description covers almost all required semantics and the crediting logic; only overhead_ms and preflight_id lack explanation, which are minor gaps given the surrounding context.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate, and it documents most of the 8 parameters with enum values for action, observed, detail, decision_basis, and baseline_direct_check, plus the identity-joining role of api_key. It leaves overhead_ms and preflight_id undescribed, so it adds substantial but not complete meaning beyond the schema.

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

Purpose4/5

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

The description states a specific verb and resource: 'tell the Guild what you did and what happened' after a guild_preflight verdict. It is clearly distinct from the sibling guild_preflight (which issues the verdict) and references its own protocol tag (AGPO-1). It is clear but not as crisp as a one-line purpose statement would be.

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

Usage Guidelines4/5

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

It states the trigger timing ('After a guild_preflight verdict') and its cost/obligation profile ('Free, no key, optional'), so an agent knows when reporting applies. It does not name alternative reporting paths or exclusions, but the context is unambiguous.

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

All agent-guild 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.