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

Annotations already declare read-only, idempotent, non-destructive and closed-world; the description adds the useful fact that no sign-in is required, and explains what the travel modes ("always", "needed", "switchable") actually mean — semantics an annotation cannot convey. It also warns that some fields only travel on record creation and that non-traveling fields are listed, which sets expectations beyond the safety profile.

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 use case, then the return shape, then the key source, then the exclusions — a sensible order. Some padding in the example list ("the phone number, the address, the due date, the line items or the tax of an invoice") and the parenthetical travel-mode glosses make it longer than strictly needed, but every block still carries information.

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 an output schema being present, the description supplies the interpretive layer the schema can't (what always/needed/switchable mean, creation-only fields, excluded fields, setup link), plus auth status, valid key source, and sibling routing. Nothing an agent needs in order to call this correctly 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?

Schema coverage is 100% with all three parameters enum-constrained and self-documented, so the baseline is 3. The description adds the operative fact that record_type keys come from find_sync_options, giving the agent a way to obtain valid values rather than guessing from the enum.

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?

States a specific verb and resource: returns which fields travel between two named systems for one record type, with the field's name in each system. It is immediately distinguishable from find_sync_options (which lists record types a pair offers) and from personal field mapping, both named explicitly.

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?

Gives the triggering question form ("whether a particular field travels between two systems for one record type") plus concrete examples, then names two exclusions with the right alternatives: find_sync_options for which record types are offered, and "not for a person's own field mapping." No inference required.

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