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

Goes well beyond the annotations: enabling is free but each planned post spends wallet credits at the quoted price, no quote/subscription/balance is required to enable, and manage:autopilot scope is needed. It also explains the optimistic-concurrency and idempotency contract (expectedUpdatedAt, clientRequestId) and the preview gate, which is consistent with destructiveHint=true rather than contradicting it.

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 core action and cost model before the procedural detail, and nearly every sentence carries operational meaning. It is dense though, packing cost, permissions, concurrency, quoting and recovery into one prose block with no structural separation.

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 destructive mutation with a five-parameter schema, a deep nested patch object and no output schema, the description covers the full decision surface: what happens with and without confirm, what it costs, what permissions are required, and how to recover from a dropped reply. The only residual gap, patch semantics, is a refinement rather than a blocker.

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%, so the description carries the load, and it does for 4 of 5 top-level params: confirm (preview vs. apply), expectedUpdatedAt (the displayed revision), clientRequestId (stable UUID for retry safety), approvedTermsHash (from the approved quote). The large nested `patch` object is left entirely unexplained, so an agent has no guidance on whether supplying it overrides saved settings.

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 ('Turn on Autopilot for this Soclo account') plus the downstream effect (plan and publish future posts to connected accounts). It references soclo_autopilot_quote and soclo_autopilot_read as related calls, but never distinguishes itself from the nearest alternative, soclo_autopilot_save, which is a real ambiguity given this tool also accepts a large settings `patch`.

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 an explicit two-step protocol: without confirm:true it previews and changes nothing; after owner approval, call with confirm:true plus expectedUpdatedAt, a stable clientRequestId and approvedTermsHash. It also names the precondition (owner must be shown saved settings and the soclo_autopilot_quote quote) and the recovery path (read soclo_autopilot_read after an interrupted reply) before retrying.

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