Sess

Show the next Sess step

sess_publish

Idempotent

Publish the next interactive form after a verified answer while keeping the same private link; pass the verified answer's revision and repeat the identical call if the outcome is unknown.

Instructions

Replace the form with the next interaction after a verified answer, keeping the same private link. Requires the verified answer for expected_revision. If the outcome is unknown, repeat the identical call.

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": {
      "handle": "<handle>",
      "expected_revision": "<expected_revision>",
      "response_event_id": "<response_event_id>",
      "interaction": "<interaction>"
    },
    "name": "sess_publish"
  }
}

Input Schema

Name	Required	Description
`handle`	Yes	Opaque handle from sess_request.
`interaction`	Yes	A Sess form: a title, components shown in order and 1-5 buttons. Keep it short: a person reads it on a phone. A value over its limit is refused with INVALID_ARGUMENTS naming the field (a JSON pointer), the limit, its length and the fix; nothing is truncated. Shorten that value and call again.
`expected_revision`	Yes
`response_event_id`	Yes	interaction.response.eventId from the verified answer.

Output Schema

Name	Required	Description	Default
`interaction`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 10, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The annotations already declare idempotentHint=true and destructiveHint=false; the description reinforces idempotency with the repeat-identical-call rule and adds that the private link is preserved and that expected_revision must come from a verified answer. What it omits is behavior on a stale or wrong expected_revision, which is the main failure mode for a mutation with optimistic concurrency.

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?

Three short sentences, front-loaded with the action and scoped by the prerequisite and retry rule; nothing is padding. The final sentence is terse to the point of being slightly cryptic about what 'outcome unknown' means.

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 no explanation, and the very large interaction schema documents its own structure thoroughly. The description covers sequence position, the revision precondition, and retry behavior, leaving only conflict/error semantics unaddressed for a four-parameter mutation tool.

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 coverage is 75%, so most parameters are already documented in structured fields. The description adds genuine meaning for expected_revision (it must be the verified answer's revision) and implies handle stability via 'keeping the same private link', but says nothing about response_event_id or the interaction payload beyond what the schema already provides.

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 gives a specific verb and object ('Replace the form with the next interaction') plus the trigger condition ('after a verified answer'), so an agent knows exactly what state change it performs. It does not name or contrast any sibling (e.g., sess_request or sess_complete), so the differentiation is inferred from the sequence language rather than stated.

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 when to call (only after a verified answer) and gives explicit retry guidance for the ambiguous-outcome case ('repeat the identical call'), which is a real usage decision point. It stops short of naming alternatives or saying when not to call, so it does not reach a 5.

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

Deploy Server