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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the confirmation protocol precisely: status='confirmation_required', an action_id and plan_token returned, and that the write only happens after confirm_action. It also explains that the opening stage is chosen server-side and that a transition-log entry is written, which are behaviors nothing else in the structured data reveals.

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 the source_id requirement, then a clearly labeled CONFIRMATION block. The rhetorical aside about reports being 'a lie' and nobody remembering the channel is editorial filler that could be trimmed, but it does not obscure structure.

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 10-parameter mutation with no output schema and no annotations beyond the safety hints, the description covers the mutation lifecycle thoroughly, including the required confirmation flow and dedupe rule. The main remaining gap is the meaning of the seven optional fields, which the description leaves entirely to an undocumented schema.

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% across 10 parameters, and the description only explains source_id (its required status and why it matters). The remaining nine — tags, currency, campaign_id, available_from, referrer_person_id, responsible_user_id, expected_salary_minor — get no meaning at all, so an agent must guess their formats and applicability.

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 opening sentence gives a concrete verb and resource ('Put a person into a vacancy's funnel' = create an application), and the follow-on detail about server-side stage resolution implicitly separates it from hr_move_application_stage. An agent can identify what this creates without opening the 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?

It states the precondition that source_id must be supplied, the constraint that only one OPEN application per person per vacancy is allowed (a second is refused), and the mandatory confirmation round-trip. It stops short of explicitly naming alternatives such as hr_move_application_stage or hr_reject_application, but the constraints are enough to route correctly.

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