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

Annotations only carry readOnlyHint=true, and the description extends this substantially: 'Reads connection state only — never calls provider APIs,' which reinforces the safety profile while adding operational specifics. It also discloses degraded-state meaning ('credential rejected by the provider — reconnect required'), the multi-bank connections[] nesting nuance, and the loop-termination rule — all behaviors an agent could not infer from annotations alone. No contradiction with readOnlyHint.

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 dense, roughly 170 words, but every sentence carries load: supersede notice, alternative routing, scope, loop contract, gate meaning, warning handling, and the read-only guarantee. It is front-loaded with the most decision-relevant fact (SUPERSEDED). The length is justified by the protocol complexity, though it demands careful reading rather than offering a quick skim.

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?

Given an output schema exists (so return values need not be spelled out), a single fully-documented optional parameter, and the readOnlyHint annotation, the description covers everything an agent needs: the full loop protocol, termination condition, human-gate semantics, warning handling, degraded-state definition, and the multi-bank structural caveat. The comparison to get_books_status also closes the sibling-selection gap. Nothing material is missing.

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 100%: org_id is fully documented in the schema, including its default, when to omit it, and the rejection condition for mismatched orgs. The description adds no parameter-specific detail, which is acceptable given the baseline of 3 for full coverage. The description's references to next_step.ask, next_step.tool, and next_step.action concern output semantics, not input parameters.

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 states a specific function: 'The agent onboarding loop driver: which providers are connected, pending, or degraded... and the ONE next step to take.' It clearly differentiates from the key sibling get_books_status by scoping this tool to the 'pure connect walk' versus 'connections PLUS every books queue.' The SUPERSEDED opening slightly muddies whether the agent should still select this tool, but the subsequent scoping statement resolves that ambiguity.

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?

Explicit routing guidance is provided: 'prefer get_books_status' for the broader coverage, with this tool retained for connect-only walks. The description also lays out a precise loop contract — 'call this, do next_step, call this again — until next_step.action is done' — plus the warning-relay protocol ('relay... VERBATIM and do not proceed without explicit confirmation') and gate semantics. This is exemplary when-to-use and how-to-use guidance.

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