ai-agent-channel

pin_set

Create or update a channel-level pinned entry by stable key, versioning each change and enforcing approval for protected keys.

Instructions

Create or update a channel-level pinned entry by stable key; every write appends a version (see pin_history). PROTECTED keys — 'team-charter', 'contract-version', 'glossary', and any key ever written with approved_by — need 'approved_by' on every version, the first included: the id of a kind='proc' proposal that (a) is for this key: its pin_key equals the key, or — only for a proposal sent without a pin_key, and only while the key has no open round — the key appears in its topic or body; (b) has a fresh 'agree' (cast after the last revision of its body and after the current pin version) from every role of its declared 'voters' — or, if it declared none, from every other role of a hosted channel, or from any other role in stdio mode; (c) was not declared void by a voter (a member of its electorate; the author withdraws a proposal with delete_message instead); and (d) has not approved a pin version before — one agreed proposal, one change. In stdio mode you must also be the proposal's sender or a recipient. Other keys are written freely; passing approved_by protects them from then on. The body should be verbatim the agreed text — not enforced, the digests below make it checkable. 'title' is at most 200 characters, 'version' at most 80. dry_run=true runs every check and returns {ok, problem, missing_agrees} without writing. Returns the written version with 'superseded' (the proposals for this key it retired). Every pin response carries 'body_sha256' plus 'body_length_bytes' and 'body_length_chars'. The hash is sha256 over the body's RAW UTF-8 BYTES exactly as stored — no normalisation of any kind (no trailing-whitespace trimming, no newline conversion, no Unicode NFC), so two parties who hash the same text always get the same number. Length is published under two explicitly named fields because 'length' alone is ambiguous for non-ASCII text, where one character can take several bytes. The server publishes these; it does NOT verify anything with them — comparing the pinned body against what was agreed is the team's check, and now it has an authoritative number to check against.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`key`	Yes
`body`	No
`title`	Yes
`dry_run`	No
`version`	Yes
`body_ref`	No
`approved_by`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 12, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Very detailed disclosure: every write appends a version, protected keys require approval with a complex validation process, dry_run behavior is described, return values are specified, and it transparently notes that the server does NOT verify the hash or length—it only publishes them for the team to check. No annotations are provided, so the description fully carries the burden, and it does so richly.

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 a single dense paragraph but is front-loaded with the core purpose in the first sentence. It uses structured lists and semicolons to organize complex approval conditions and hashing details. While long, every sentence contributes essential information; the length is justified by the tool's complexity.

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?

Given the tool's complexity (7 parameters, approval logic, hashing, dry_run), the description covers all critical aspects: how to use it, return values, edge cases, and the team's verification responsibility. The only minor gap is 'body_ref', but it's not essential to the core operation. An agent has enough information to call the tool correctly without further clarification.

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?

The description adds significant meaning to several parameters: it explains the role of 'approved_by' (proposal id), 'dry_run' (runs checks without writing), and clarifies constraints on 'title' and 'version'. However, 'body_ref' is not explained at all, and the schema has zero description coverage, so the description compensates for most but not all parameters. It adds value beyond the schema but leaves one parameter ambiguous.

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 and resource ('Create or update a channel-level pinned entry by stable key'), and implies the distinction from siblings like pin_get, pin_list, and pin_history by referencing versioning and history. An agent can clearly tell this is the write operation for pins.

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?

Provides explicit guidance on when to use the tool, including the approval requirement for protected keys, the dry_run option for testing, and the condition that other keys are written freely. It does not explicitly name alternatives for reading, but the context (versioning, history) makes it clear that pin_get/pin_list/pin_history are for retrieval, so usage is well implied.

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