build_table

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

With no annotations, the description must fully disclose behavior. It mentions applying style, freezing header, banding, autofitting, and number formats, but omits critical details: the structure of the 'rows' parameter, whether existing data at the anchor is overwritten, the effect on the spreadsheet (except preview mode), and what happens if the headers array length mismatches rows. The missing explanation of 'rows' is a significant gap.

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 reasonably concise, with a single paragraph that front-loads the main purpose. Every sentence adds value, but the omission of key parameters like rows and headers means it is not as efficient as it could be.

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?

Given the tool has 10 parameters (4 required) and no output schema, the description is incomplete. It explains anchor, style, preview, and number_formats but ignores the crucial 'rows' and 'headers' parameters, which are required. It also does not describe the return value or confirm the action when not in preview mode. Overall, the agent would lack essential information to invoke the tool 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 coverage is 0%, so the description must add meaning. It provides examples for anchor (Sheet1!A1), lists valid options for style (clean/financial/report-header/input), explains preview behavior, and gives a number_formats example. However, it fails to explain the 'rows' and 'headers' parameters, which are central to the tool's function. The boolean parameters autofit, banding, freeze_header are mentioned as behaviors but not explicitly linked to their parameter names, causing potential confusion.

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 tool writes a titled table and formats it in one shot. It specifies the verb 'write' and resource 'titled table', making the main purpose clear. However, it does not explicitly differentiate from sibling 'add_table' which might also create a table, though the one-shot formatting aspect distinguishes it.

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 lacks any guidance on when to use this tool versus alternatives like add_table followed by apply_style_preset or format_cells. There is no mention of prerequisites, when not to use it, or which situations are best suited.

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