beel_patch_by_id

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

Annotations only declare readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description goes far beyond: it explains immutability of `nif`, `entity_type`, `legal_form`, the AEAT census re-validation for `legal_name`, the write-only nature of most fields, the return type `CompanyData` that excludes the request body, and the exact live/test restrictions. This fully discloses side effects and response behavior without contradicting any annotation.

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 long but well-structured: it starts with the core purpose, then immutability, live/test rules, return behavior, and finally guardrails. Each paragraph carries essential information and the guardrail section is clearly separated. It could be slightly tightened (e.g., merging some repetitions about write-only fields), but the length is justified by the complexity of the rules.

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?

Despite lacking an output schema, the description covers return semantics (what `CompanyData` carries, which fields are read back from other endpoints), references the exact endpoint (`PATCH /v1/companies/{company_id}`), and points to exhaustive documentation. It also mentions the account/context derivation and the `BeeL-Active-Company` header non-involvement, which is essential for correct invocation. Nothing critical is missing.

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?

Although the schema already provides descriptions for each field (NIF format, immutability notes, etc.), the description adds critical operational semantics: it distinguishes the six fields writable from Test on a Live company, clarifies that the rest are write-only and answered with `422`, and specifies that sending a field its current value is never a change. This goes beyond the schema's per-field descriptions and directly guides parameter choice.

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 verb ('Updates') and a precise resource ('editable fields of a company (NIF)'), and immediately scopes the field set to `UpdateCompanyRequest`. It differentiates from related operations by focusing on the patch semantics and by detailing immutability rules, which makes it unambiguous among the sibling tools that also write company data (create, activate, deactivate).

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 gives explicit when-to-use context: it enumerates which fields are writable from Test on a Live-activated company, which fields trigger AEAT re-validation, and what error (`422 FISCAL_IDENTITY_LIVE_ONLY`) results from disallowed writes. It also directs the agent to `beel_docs_search` for exhaustive rules, and the guardrails pointer adds a resource-specific prerequisite. This clearly conditions invocation on credential mode and field selection.

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