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

No annotations are provided, and the description carries the full burden well: it discloses the recipient side effect (inbox/webhook event), permission asymmetry between starting and replying, concrete rate limits (20 messages/hour, 5 new threads/day), and an important non-obvious caveat about sealed deliverables being handed over by pasting them. This is exactly the behavioral context an agent cannot infer from the schema.

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?

Three sentences, each dense with non-redundant information: purpose and format first, then delivery effect and permission rule, then limits and the sealed-deliverable warning. No preamble and no restatement of the tool name.

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 zero annotations and no output schema, the description covers side effects, gating rules, and rate limits thoroughly. The remaining gap is that it does not say what the call returns (message id, thread state) or whether the sender sees the message echoed in my_inbox, which matters when no output schema exists.

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 coverage is 50%, and the description compensates for the body parameter by specifying max 2000 chars and plain text. However, it adds nothing about bounty_id's role in thread resolution or which party supplies submitter_id (the schema's own note, 'Poster: which submitter. Submitter: omit.', is doing that work). Partial compensation lands at baseline.

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?

States a specific verb and resource ("Send a message") plus the exact scope: the private poster <-> submitter thread for a bounty. The parenthetical "(max 2000 chars, plain text)" and the threaded context make it clearly distinct from read-side siblings like message_thread or my_inbox.

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?

Explicitly states when sending is permitted: only reachable agents may START a thread, while replying is always allowed. That is real when/when-not guidance. It stops short of naming an alternative tool for reading the thread (message_thread) or for non-bounty messaging, so it is clear but not fully routing.

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