sage_message_reply

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

With no annotations, the description carries full burden and meets it extensively. It discloses session checks, legacy provider fallback behavior (no fallback on canonical denial), idempotency semantics (identical retry returns original, different retry conflicts), and post-failure procedures (refresh inbox, handoff only visible other-session claim, otherwise stop). This is rich behavioral context that an agent needs to reason about outcomes.

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?

The description is long but every clause serves a purpose—no filler. It front-loads the core purpose in the first sentence, then logically flows through behavioral nuances and failure handling. The length is justified by the tool's complexity, though it could be slightly tighter without losing information.

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?

The tool is complex (multiple reply types, idempotency, failure paths) and lacks an output schema. The description covers the essential aspects: what identifies the message, what happens on retries, how legacy paths are chosen, and what to do on failure. There is no mention of return format for successful replies, but the idempotency statement implies original result/event is returned. Overall, nothing critical is missing for an agent to call it correctly.

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%: only 'result' has a description, missing 'message_id'. The description adds context that message_id must come from sage_messages_receive or sage_inbox, which clarifies its origin but does not detail format or constraints. For 'result', the schema already says 'Untrusted result data returned to the sender' and the description adds no further semantics. Given the partial coverage, the description modestly compensates but does not fully elaborate on parameter meaning.

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 and resource: 'Reply to one receiver-local, provider-addressed legacy, or inbound federated message_id' and names the source functions (sage_messages_receive or sage_inbox). It clearly differentiates from sage_message_send by explicitly forbidding substitution, and from sage_message_replies and sage_inbox by context. The purpose is unambiguous and distinct from siblings.

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 states when to use (for replying to messages from receive/inbox), when not to (do not create a substitute send unless independently authorized), and gives conditional paths (legacy provider selection only after typed compatibility signal). It also advises on handoff and failure handling, providing explicit exclusion criteria. This is exemplary usage guidance.

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