start_onboarding_run

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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent, closed world), so the description's added value is the workflow disclosure: which phases run, where execution halts, and what is returned. The phrase 'read-only onboarding' sits in tension with readOnlyHint=false, though it reads as describing source-side non-mutation (consistent with destructiveHint=false) rather than the tool's own side effects.

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?

Three short lines, front-loaded with the action and followed by execution scope and return behavior; no filler. Slightly marred by the ambiguous 'read-only' qualifier, which is the one phrase that could mislead.

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 stateful pipeline-start tool in an eleven-tool suite, the description covers execution and terminal state well, and an output schema exists so return details needn't be repeated. However it omits prerequisites, permission requirements, and how it relates to resume_run / list_pending_reviews, which an agent needs to sequence calls correctly.

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 both parameters, so the description carries the full burden, yet only 'connection_id' is implied via the 'registered source (e.g. fixture:portco_a)' example. The optional 'company_id' parameter is never mentioned or explained, leaving its scoping role 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 and resource ('Start ... onboarding of a registered source') and enumerates the pipeline phases it executes (validation, profiling, entity/join inference, canonical mapping). It also distinguishes itself from the sibling 'resume_run' by framing this as the initial start that halts at the first human review gate.

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?

The stopping condition ('stops at the first human review gate') implies the natural follow-up (list_pending_reviews / resume_run), but no explicit when-to-use or when-not-to-use guidance is given and no alternative is named. An agent must infer the relationship to the ten sibling tools.

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