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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavior: `source: ai` consumes AI credit and surfaces a `note` the agent should relay, and `manual` removes the existing autofill. It stops short of describing reversibility or what happens to already-written values beyond the keepUpdated default note.

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?

Front-loaded with the core action, then one clause per source mode, then the naming rule. Dense but every clause carries information; the heavy em-dash compression costs a little readability but no sentence is wasted.

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 an output schema present, the description does not need to explain return values, yet it still calls out the `note` field where it matters. Nested `when` semantics and keepUpdated defaults are documented in schema, and the description covers the mode-selection and naming contract that complete the picture for an 8-parameter mutation tool.

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 already 88%, so a baseline 3 applies, but the description adds real meaning: `field` names must match what `sheet.schema` lists, `formula` uses brace-referenced fields, and `readFields` is by name. These tie the AI and formula parameters to the naming contract the schema alone does not state.

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 opens with a specific verb phrase and resource: make a field fill itself on an existing sheet, or stop it. The three modes (ai, formula, manual) sharpen the scope enough that an agent can distinguish this from siblings like sheet.update_attribute or sheet.set_dependencies without opening either schema.

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?

It gives explicit selection logic among the three sources — AI writes from an instruction reading readFields, formula computes from braces, manual removes autofill — plus the unknown-field-name refusal behavior. It does not explicitly contrast against sibling tools such as sheet.update_attribute, which keeps it short of a 5.

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