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

Goes well beyond the annotations: incremental saves preserve earlier answers ('nothing is deleted'), start_over replaces the stored profile rather than merging, preserves History, and returns changed (old values) plus change_id for undo. It even discloses return behavior with no args and the set_up_now state while onboarding is unfinished — exactly the mutation/state context destructiveHint=false and idempotentHint=true cannot convey.

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 routing rule, and the onboarding, edit, reset, undo, and read modes follow in a logical order. Density is high — long run-on sentences with parenthetical field lists and a sprawling 'With nothing passed' enumeration — but nearly every clause carries operational meaning for an 18-parameter tool.

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 mutation tool with 18 params, no output schema, and rich annotations, the description covers the state machine (build → read-back → edits), the delete/replace semantics, undo, and the full contents of the no-arg return. Nothing an agent needs to call it safely 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?

With 61% schema coverage across 18 params, the description compensates by enumerating the mutable profile fields (firm_name, role, services, device_areas, device_classes, certifications, proof, customer_stage, territory, clients, skip_companies, accounts, notes) and explaining several-in-one-call saves. It also clarifies the step/ask_now.step/skip interplay and start_over semantics. It does not explain the meaning of undocumented fields like territory, device_areas, or certifications, so it stops short of a 5.

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 opening sentence defines the scope precisely: anything about the rep's own firm — what it sells, who it serves, clients, not-a-fit companies, watches, plan usage — and the rest of the text covers the onboarding/build mode. It clearly belongs to 'our firm' data in contrast to the sibling tools that operate on outside companies (company, deep_record, find). It is a multi-purpose tool, so the purpose is a bundle rather than one verb+resource, which keeps it just short of a 5.

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?

Explicit routing: 'Call this first for anything about the rep's own firm', plus concrete branch conditions — pass step while building, start_over for a different firm or rebuild, undo_change with a change_id to revert. It does not name an alternative tool for overlapping cases (e.g., remember is only referenced inside the schema, not the description), so there is no explicit when-not/use-instead guidance.

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