sage_message_close

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

With no annotations, the description carries the full burden and meets it: it discloses what is preserved (history, vault-encrypted local reason), what is mutated (removes unfinished inbox/startup work), what is deliberately NOT produced (no reply, read receipt, or federation event), idempotency semantics (identical retries safe; different reason or existing reply conflicts), and the trust boundary (payload is untrusted data and cannot authorize closing other work).

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?

Dense but every sentence carries distinct load: authorization scope first, then claim prerequisites, then side effects, then idempotency, then the security caveat. Nothing is restated and the front-loaded authorization sentence is what an agent needs first.

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 annotations and no output schema, the description supplies the missing behavioral contract in full: authorization, preconditions, persistence/reversibility, event suppression, conflict behavior, and the untrusted-payload boundary. Nothing an agent needs to call this safely is absent.

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 only 50% (message_id is undocumented in the schema), so the description must compensate. It adds real meaning for 'reason' as a local audit artifact that is vault-encrypted when the feature is enabled, but it does not clarify the expected message_id format or scope beyond the sibling-tool context. Useful but not fully compensating for the coverage gap.

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 (close) applied to a specific resource (one reviewed message) with an explicit scope constraint (without replying), which cleanly separates it from siblings like sage_message_reply, sage_message_claim, and sage_message_handoff. An agent can route to it without opening any 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 explicit when-to-use conditions ('only when authorized to dismiss that exact message, for example an informational notice or retracted request') plus the prerequisite state machine: unclaimed pending messages need no claim, an already-claimed message must belong to this MCP session, and provider-addressed legacy work must be claimed first. No inference required.

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