beel_get_setup_status

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

The annotations already establish readOnlyHint, idempotentHint, destructiveHint=false and a closed-world surface, so the description is not carrying the safety burden. It adds genuine behavioral context beyond them: readiness is evaluated against the session's environment (Test vs Live, surfaced as `environment`), and a section that cannot be read carries an `error` and never a default, so unknowns are never reported as ready. That non-defaulting contract is exactly the kind of semantic guarantee annotations cannot express.

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?

Every clause carries information — there is no filler or repetition of the annotations. The weakness is structural: the first sentence is a single ~90-word run-on with deeply nested enumerations, which would read far better as a short lead plus a bulleted field list. Front-loading is good (read-only status and the ids come first).

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?

An output schema exists, so return shape need not be spelled out, yet the description usefully frames the per-company contents and the error-vs-default rule. Combined with full parameter schema coverage and rich annotations, an agent has what it needs to call and interpret this correctly. Only the sibling routing gap keeps it from a 5.

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?

There is a single optional parameter and schema description coverage is 100%, with the schema itself clarifying that company_id is a UUID and not the NIF. The description adds no filtering semantics beyond that, which is fine given the coverage, but it also never mentions that the report can be scoped to one company. Baseline 3 for high-coverage schemas.

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 resource and scope: read-only setup status across the account, per company, including company_id/NIF, environment, blockers, default series, VeriFactu status, tax defaults and a recommended next action. An agent can tell this is an aggregated readiness report rather than a single-resource getter. It never names the siblings it overlaps with (beel_get_issuing_readiness, beel_get_default_series, beel_get_verifactu_configuration, beel_get_tax_configuration), so differentiation is left implicit.

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 phrase 'with the ids an integration needs' implies the onboarding/integration-setup use case, and 'the single recommended next action' implies it is a first-stop diagnostic. However, there is no explicit when-to-use or when-not-to-use statement and no routing to the narrower sibling getters. Usage is inferable but not stated.

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