Update Autofill Profile

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

Goes well beyond the annotations (destructiveHint/idempotentHint) by spelling out merge semantics per section, that null removes a key, that education/languages replace the list whole, that saved custom answers are never removed here, and that unknown section/key/market writes nothing. Also discloses the return shape {profile, setup} and that setup is null on read failure, which no output schema covers.

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 purpose and every sentence carries substantive rules, but the custom-answer rule in particular is a long nested clause that takes rereading, and the whole thing is one dense paragraph rather than grouped by section.

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?

For a destructive, all-optional merge-write with no output schema, the description covers the merge/removal model, the custom-answer identity rule, what is deliberately out of scope, failure behavior for unknown keys, and the returned object — leaving no material gap for correct invocation.

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 only 14%, so the description must compensate, and it does: it explains per-section key-level merging, null-removal, list replacement for education/languages, and the question/only_for/only_for_kind matching rule for custom answers. It stops short of naming individual fields inside personal/preferences/eligibility, which the nested $defs already document.

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?

Opens with a specific verb and resource ('Save the user's application-form answers') and immediately ties it to the sibling read tool get_autofill_profile and to the Companion consumer, so the agent knows exactly what is being written and who reads 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?

Routes the agent clearly: reads go through get_autofill_profile, removals and EEO answers are 'the user's, in Profile' and not this tool, and work-permit answers are keyed per country with market keys from apply_in. No explicit contrast against write-side siblings like record_filled_answers, so not a full 5.

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