Quiet Menders MCP Server

qm_clinic_diagnose

Analyze symptoms or a transcript to identify prompt injection, contradictions, loops, context bloat, exposed secrets, and duplication, returning severity, evidence, cleaned context, and next steps.

Instructions

Restore Clinic diagnosis: describe symptoms or paste a transcript/context and receive a structured read of likely conditions encountered (prompt_injection_indicator, possible_contradiction, loop, context_bloat, secret_or_pii_exposure, duplicated_content), each with severity, evidence, and detail, plus a cleaned redacted context safe to carry forward and suggested next steps. Anonymous — only aggregate counters are kept; content is never stored. Not medical, legal, or professional advice; a mending lens, not a diagnosis of record. Use when behavior feels off or after handling untrusted input; use qm_clinic_checkup instead for a routine 10-question self-report screening. Example: transcript= returns findings with severities, a human-readable summary, and cleaned_context safe to hand off.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`transcript`	Yes	Symptoms or transcript to read (max 20000 chars).

Output Schema

TableJSON Schema

Name	Required	Description
`at`	No	ISO timestamp of the diagnosis.
`ok`	No
`input`	No
`clinic`	No	Clinic engine version.
`counts`	No
`summary`	No	Human-readable finding count by severity.
`findings`	No
`stats_note`	No
`cleaned_context`	No	Redacted, deduplicated context safe to carry forward.
`suggested_next_steps`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses anonymity, non-retention of content, non-advice status, redaction/cleaning behavior, and the 'not a diagnosis of record' framing. These are meaningful behavioral constraints beyond what the schema conveys.

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 long but every clause earns its place: output format, privacy, disclaimer, usage guidance, and example. It is front-loaded with the core purpose and output, though the legal-style disclaimer adds length without being strictly necessary for invocation.

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

Completeness5/5

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

For a one-parameter tool with an output schema, the description is exceptionally complete: it covers input, expected findings, return values, privacy, caveats, alternative tool routing, and a worked example. Nothing needed for correct invocation is missing.

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 100%, so the baseline is 3. The description adds value by explaining what kinds of content belong in transcript (symptoms, session transcript, context) and giving a concrete example, though it does not deeply extend beyond the schema.

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?

States a specific verb (diagnose), resource (clinic), input (symptoms/transcript), and output (structured findings with severity/evidence/detail, cleaned context, next steps). The list of detected conditions makes it distinct from sibling tools like qm_clinic_checkup.

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

Usage Guidelines5/5

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

Explicitly says when to use it ('when behavior feels off or after handling untrusted input') and names the alternative qm_clinic_checkup for routine self-report screening. The example further clarifies the expected input and return shape.

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