Send a reply

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

Adds substantial context beyond annotations: irreversibility ('cannot be taken back'), the 24 hour window, opt-out exclusion, per-key rate limit, required Publish scope, the side effect of pausing automations in the conversation, and precise retry semantics for idempotency_key. The annotations declare destructiveHint=false and idempotentHint=false; the description's 'cannot be taken back' and retry-key behavior are consistent with those (the key is what makes the retry safe), not contradictory.

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?

Irreversibility and the confirm-first instruction are front-loaded, followed by hard constraints, side effects, auth, and retry guidance in that order. Every sentence carries a distinct, actionable fact with no restatement of the name or 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 open-world, non-idempotent mutation with no output schema, it covers side effects, preconditions, auth and retry. The only real gap is what the call returns on success (a message id or conversation state), which the agent may need to chain follow-up actions, and no return shape is described.

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 100%, so text, conversationId and idempotency_key are already documented in the schema, including the 1000 character cap and the id pattern. The description reinforces the retry use of idempotency_key but adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

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 ('Sends a direct message reply'), scopes it to one Inbox conversation, and anchors it to the product behavior an operator already knows ('the same as Send in the Inbox'), which cleanly separates it from the sibling postfjord_draft_reply. An agent can tell what this tool does without opening the schema.

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?

Gives real eligibility conditions — only inside the 24 hour reply window, never to an opted-out person, 10 replies/minute per key — and a procedural precondition ('Confirm the exact text with the person you work for before you call this'). It never names the alternative sibling (postfjord_draft_reply) or explicitly says when to prefer it over sending, so 4 rather than 5.

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