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

It discloses that the tool internally executes two Jobs and merges results, and it explicitly states that account linking is not required and links resolve per leg provider. It also flags session dependencies. These details add meaningful behavioral context beyond the annotations, which only provide readOnlyHint=false and destructiveHint=false.

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 sentences, each carrying distinct information: composition, internal jobs, merge behavior, session prerequisites, and account-link semantics. There is no filler, and the most important facts are front-loaded.

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?

It covers the tool's composite nature, target institutions, merge behavior, and session/account-link preconditions, which are the main non-obvious facts an agent needs. It does not spell out return/error shape, but as a smoke tool the purpose is reasonably clear and the schema/annotations cover the rest.

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?

The only parameter, idempotency_key, is already fully described in the input schema with 100% coverage, including deterministic derivation of leg keys. The description adds no parameter-level semantics, so the baseline score of 3 applies.

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 opens with 'Composite smoke tool' and names the exact internal jobs (hometax.session.user_info, nhis_edi.session.status) plus the merge behavior, so an agent knows both what and how it operates. This clearly distinguishes it from sibling payroll_pack generate tools and individual session/status tools.

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 description provides clear usage context by labeling the tool as a smoke/health-check composite and stating the critical precondition that sessions must already be logged in per institution. It does not explicitly name alternatives or exclusions, but the composite framing and prerequisite are enough for an agent to infer when this tool applies.

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