get_values

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

No annotations exist, so the description carries the full burden. It usefully discloses the return shape (slots with path/template/value-or-error, plus tables rows) and a subtle precedence rule ('unless the live record brings the document's own' timezone), but never states that it is read-only/side-effect free or how missing expressions or errors surface.

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 return structure is front-loaded in the first sentence, followed by mode selection, cost guidance, and formatting options. Dense but every clause adds information; the parenthetical field list earns its space since there is no output schema.

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, describing the slots/tables return shape is a real contribution, and formatting options are covered. However, three of seven parameters are undocumented and all parameters are optional with no stated defaults or required combination, leaving an agent unsure what a minimal valid call looks like.

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 coverage is 0%, and the description explains 4 of 7 parameters meaningfully: layout vs template_id, language's formatDate presets, and timezone as IANA with an example. Three parameters (model, mapping, record_id) receive no explanation at all, and record_id in particular is central to 'one record'.

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 effect: it reports what each `{{ }}` expression evaluates to for a single record, broken out per slot and per table row. The clause about being 'the cheapest way to check expressions without reading a PDF' implicitly separates it from render_preview, though the core verb ('evaluate') is never stated outright and the phrasing leans on template jargon.

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?

'Pass template_id for a saved template or layout for a draft' gives concrete routing between the two modes. The 'cheapest way to check expressions' line hints at when to prefer this over render_preview, but there is no explicit exclusion or prerequisite (e.g. when a rendered PDF is actually required).

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