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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds material context beyond them: cost is free, no work is started, the read:accounts authorization scope is required, and expectedUpdatedAt is null when nothing is saved and must be echoed into later changes. The request-ID ledger caveat discloses a subtle correctness limitation. These are genuine behavioral disclosures, not restatement of annotations.

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?

Purpose and scope are front-loaded in the first sentence, and subsequent sentences each add distinct information (cost/behavior, auth, revision handling, ledger caveat). It is dense but largely waste-free, though the final ledger sentence is somewhat esoteric and wordy relative to its value.

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?

With no output schema, the description adequately characterizes the return (configuration plus expectedUpdatedAt, null when unsaved) and covers safety, authorization, and downstream revision handling. The main gap is the undocumented clientRequestId input, which is the only incomplete element for an otherwise simple read tool.

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% for the single clientRequestId parameter, so the description must compensate, but it never explains clientRequestId, its format, or that it functions as an idempotency key. The ledger sentence touches request IDs only tangentially and does not clarify the parameter's role. The meaning of the one input is left undocumented.

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 (read) and resource (saved Autopilot account configuration), enumerates its contents (schedule, limits, approval choices) plus the expectedUpdatedAt revision. 'Free; changes nothing and starts no work' directly distinguishes it from mutating siblings like soclo_autopilot_enable, pause, run, and save. An agent can tell this apart from sibling reads without opening a 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 clear usage context: it is free, read-only, requires read:accounts, and its expectedUpdatedAt must be preserved for any later change, making it a prerequisite to update flows. It does not explicitly name sibling reads (e.g. status/runs) or state when not to use it, so exclusion guidance is inferred rather than stated.

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