send_message

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

With no annotations, the description carries the full burden and does so well: it discloses that response_timeout_seconds is pure metadata with nothing timed, deleted, or resent, that duplicate (sender, dedup_key) inserts return the existing message with duplicate=true, and that conversation sends are validated atomically with an in-flight limit and turn limits that reject and move to needs_human. These are non-obvious side effects an agent could not infer.

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?

Front-loaded with the one-line purpose, then organized by topic (reply/timeout, dedup, conversation semantics). It is long, but nearly every clause carries operational detail; the parenthetical 'e.g. a task id' is the only clearly disposable fragment.

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 7-parameter mutation tool with no annotations and an output schema present, the description covers side effects, idempotency, validation failure modes, and parameter interactions. Nothing an agent needs to call it safely is missing, and return values are correctly delegated to the 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% across 7 parameters, so the description must compensate and does: it defines reply_to, dedup_key semantics, conversation_id inheritance from reply_to, the clamp range and default persistence for response_timeout_seconds, and the three kind values with their differing wake behavior. Only recipient and text are left implicit, which is reasonable given their 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?

States a specific verb and resource ('Send a message to another agent') and pins down the implicit sender identity ('this process's AGENT_ID'), which the agent could not know otherwise. It is immediately distinguishable from the receiving-side siblings (receive_messages, claim_message, release_message).

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 concrete conditional guidance: use reply_to to answer requests, use dedup_key for idempotent retries, pass conversation_id/kind for dialogue sends, and omit kind for a plain message. It also directs behavior after a deadline ('report it and wait for human direction'). It stops short of explicitly stating when to prefer start_conversation over a plain send, which is the main missing routing cue.

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