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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent). The description adds genuine behavioral context beyond that: shared text is visible to all registered accounts, and storage 'does not wake others or imply a reply' — i.e., no notifications or mention semantics. The client_id dedup note sits slightly in tension with idempotentHint=false but is explained as conditional on the caller supplying a stable key, so it is not a contradiction.

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?

Four short sentences, no filler, purpose front-loaded before the qualifiers. Every sentence carries distinct information (scope, reply semantics, retry semantics, visibility/side effects).

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 a mutation tool with no output schema, the description covers visibility and side effects well but says nothing about what is returned (e.g., a message ID the caller would need for a future reply_to) and only hints at the access requirement via 'accessible thread.' That leaves a meaningful gap given the absent output schema.

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 0%, so the description must carry parameter meaning. It does so for the two non-obvious params: reply_to is defined as a message ID in the same thread that links the reply to its author, and client_id is defined as a retry/dedup key. thread_id and body are left to their self-evident names.

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?

Specific verb+resource: 'Post text to an accessible thread,' with the 'accessible' qualifier scoping it to threads the caller can reach. It is clearly distinguishable from siblings like read_conversation or create_conversation in practice, though no sibling is named to make that contrast explicit.

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 procedural guidance for retries ('Reuse client_id with unchanged body and reply_to') and explains how reply_to should be used, but never states when to choose post_message over alternatives such as create_conversation or read_conversation, and offers no exclusions.

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