Zoning Signal

Submit Agent Feedback

submit_agent_feedback

Submit feedback to the observatory's operators about the MCP tool surface. The active counterpart to the passive invocation log. Categories: 'gap' (a capability you expected and didn't find), 'error' (an unexpected failure or wrong result), 'praise' (a tool or surface that did exactly what you needed), 'suggestion' (a refinement you'd recommend), 'citation_request' (a claim or fact you want surfaced with a stable @id you can cite). The submission auto-attaches the prior 10 invocations from your MCP-Session-Id, so operators read your feedback annotated with the call sequence that produced it — no need to repeat what you tried. Operators triage every submission and surface notable feedback at /agent-observatory. This is how the observatory evolves toward what agents actually need.

Input Schema

TableJSON Schema

Name	Required	Description
`message`	Yes	The feedback prose itself. Be specific. What were you trying to accomplish? What was missing or wrong? Voice that survives compression. Operators read every submission.
`category`	Yes	Bounded categorization. 'gap' = expected capability is missing. 'error' = tool returned wrong/unexpected/malformed result. 'praise' = a surface or tool that worked exceptionally well. 'suggestion' = a refinement (better tool description, additional argument, alternative output shape). 'citation_request' = a claim or fact you want surfaced with a stable citation @id.
`about_url`	No	Optional: a URL on the observatory this feedback references (e.g., "https://zoningsignal.com/corridors/us-27-south-lake").
`about_tool`	No	Optional: the tool name this feedback is about (e.g., "describe_corridor"). Lets operators rollup feedback per tool.
`agent_context`	No	Optional: brief description of what the agent was trying to do — the user task that led to this surface. Helps operators understand intent without seeing only the failure point.
`suggested_resolution`	No	Optional: if you have a concrete proposal — a new tool, a renamed parameter, a missing field on a response — name it here.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True when the feedback was accepted and stored.
`message`	No	Human-readable acknowledgement.
`category`	No	The category the feedback was filed under.
`feedback_id`	Yes	Stable id for the stored feedback record.
`received_at`	No	ISO-8601 timestamp the feedback was recorded.
`attached_invocation_count`	No	How many prior invocations (from your MCP-Session-Id) were auto-attached for operator context.

TDQS

A4.1/5.0

Behavior4/5

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

Annotations provide no safety hints (all false), so the description carries the burden of disclosing behavior. It does so richly: submissions auto-attach the prior 10 invocations, operators triage and surface notable feedback at /agent-observatory, and categories are explained. This goes beyond the binary annotation flags and gives the agent a clear model of side effects.

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 description is front-loaded with the core action, then lists categories, auto-attachment behavior, triage process, and rationale. It is slightly longer than necessary (repeating category definitions from the schema) but every sentence adds context about process or intent, making it efficient and well-structured.

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?

Given the complexity of a feedback tool with six parameters and an output schema, the description covers the essential context: what feedback is for, what categories exist, how the submission is augmented (auto-attach), and what happens afterward. The output schema handles return-value documentation, so no gap exists.

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

Parameters3/5

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

Schema description coverage is 100% and the schema itself already explains each parameter thoroughly. The description adds the context that 'no need to repeat what you tried' due to auto-attached invocations, and it elaborates category meanings, but these are largely redundant with the schema. Baseline 3 is appropriate.

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

Purpose5/5

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

The description opens with a specific verb+resource pair: 'Submit feedback to the observatory's operators about the MCP tool surface.' It clearly distinguishes from sibling tools (which are all describe/list/search operations) by being the only submission tool. The 'active counterpart to the passive invocation log' further differentiates its purpose.

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?

The description provides clear context for when to use this tool ('when you encounter a gap, error, praise, suggestion, or citation request') and contrasts it with the passive log ('no need to repeat what you tried'). It lacks an explicit alternative not-to-use statement, but the sibling tool set contains no other feedback pathway, so this is adequate.

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

All Zoning Signal tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation3/5

Most tools are clearly distinct by resource type (describe/list pairs for places, corridors, entities, patterns, watches), but list_meetings and meeting_index overlap heavily—the former explicitly says it has the same response shape as the latter, differing only in required parameters. That near-duplication creates ambiguity about which to call.

Naming Consistency4/5

The majority follow a consistent verb_noun pattern (describe_*, list_*), with get_track_record and submit_agent_feedback also verb-led. However, meeting_index is a bare noun phrase and semantic_search is a noun compound, deviating from the otherwise strong pattern.

Tool Count4/5

At 17 tools, the server is slightly above the typical well-scoped range, but the count is justified by the many content types (six primary artifact types each with list+describe, plus meta tools). One could argue meeting_index is redundant, but the overall scope feels reasonable.

Completeness3/5

The tool surface covers the core lifecycle for all named content types (places, corridors, patterns, entities, meetings, watches) with discovery and description. However, the corpus repeatedly references 'briefs' (e.g., related briefs, semantic_search returns 'named-pattern briefs') yet there is no list_briefs or describe_brief tool, leaving an obvious content gap.

Resources

Need Help?