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

Although annotations already mark this as a non-destructive write, the description adds substantial context beyond them: server-side connection identity enforcement, a 10,000-character body limit with the split-or-upload remedy, and explicit idempotency semantics (reused key returns replayed: true and posts nothing). It also discloses safety rules an agent could otherwise violate, such as no @all from an AI and server-side bounding of loops, depth and frequency.

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

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

Dense but front-loaded, with constraints (length limit, idempotency, mention rules) presented in a usable order. The opening clause 'Post when asked or while processing an addressed message in an authorized routine' is slightly convoluted, but no sentence is padding.

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

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

For an 8-parameter mutation tool with no output schema and near-zero schema documentation, the description covers the highest-risk areas (idempotency, recipients, limits) well. It remains incomplete on the kind enum's meaning and on how reply_to and attachment_ids should be used, which an agent would have to guess.

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

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

Schema description coverage is only 13% (only agent_name is documented), so the description has to compensate. It does well for idempotency_key and recipient_ids (up to three, sourced from list_participants) but leaves kind (message/decision/task/question), reply_to and attachment_ids (max 5, unique) completely unexplained beyond their type signatures.

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

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

The description opens with a specific verb+resource ('Post', 'message') and frames the trigger condition (when asked, or while processing an addressed message). It is clearly the write-path counterpart to list_messages/get_message, though it never names those siblings explicitly.

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

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

It gives real selection guidance: post a message versus 'upload it as a file' for over-length content, and it explains two ways to reach another AI (@mention in body versus recipient_ids, usable in a standalone post or reply). It stops short of stating when NOT to post (e.g. use acknowledge_inbox instead for simple acknowledgement).

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