beel_get_invoice_customization

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds helpful context that customization is per-NIF and that the account is derived from company_id, reinforcing the open-world nature. It does not contradict annotations. However, it does not disclose additional behaviors beyond the annotations and the parameter details, which are already extensive in the schema. The description contributes modestly but not substantially beyond the annotation coverage.

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 concise and well-structured: it front-loads the primary purpose, clarifies the per-NIF scope, points to the related options endpoint, and gives the exact HTTP endpoint. Every sentence adds value with no redundancy. The length is appropriate for the tool's complexity.

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?

With no output schema, the description adequately lists the returned fields (PDF template, accent colour, invoice language, email language, current logo) so the agent knows what to expect. It also provides the endpoint and references the options endpoint for additional context. The parameter description covers error conditions. The tool is a straightforward read operation, and the description combined with annotations and schema fully equips the agent to call it 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 100% and the single parameter 'company_id' already has a rich description explaining its role, the derivation of the account, the irrelevance of the BeeL-Active-Company header, and 403 error behavior. The description adds the fact that customization is per-NIF, which is informative but does not significantly augment parameter meaning beyond what the schema already provides. This aligns with the baseline of 3 for high schema coverage.

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 clearly states the verb 'Returns' and the resource ('how the invoices of a company are rendered and delivered') and enumerates the specific data returned: PDF template, accent colour, invoice language, email language, and current logo. It also distinguishes this from related tools by noting that the catalogue of templates is served by a separate endpoint, effectively differentiating it from list/option tools. This is specific and unambiguous.

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 implies usage by stating what the tool returns, and it refers to the alternative endpoint for obtaining the catalogue of templates and suggested colours. It does not explicitly name the sibling tool 'beel_list_invoice_customization_options', but the reference to the endpoint guides the agent. However, it lacks a direct contrast such as 'Use this for per-NIF customization; use the options endpoint for the available templates.' Overall, the context is clear but exclusions and explicit alternatives are not fully articulated.

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