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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: it normalizes spelling and phone-number variants before comparing, and it explicitly disclaims live verification, ownership checks and truth validation of master data — all of which affect how results should be interpreted.

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?

Two sentences, front-loaded with the core action and scope, then the normalization and disclaimer clauses. The field enumeration is long but each item corresponds to a real schema property; no filler sentences.

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?

There is no output schema, yet the description never indicates what the comparison returns — per-field mismatches, a diff report, match/mismatch flags — nor how many profiles can be compared at once. For a read-only diff tool with a deeply nested two-parameter schema, that leaves the agent guessing about result shape.

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 0% and the schema is heavily nested (reference object plus a profiles array of objects), so the description must compensate. It does map its field list onto several schema properties (phones, public_address, hours, service_areas, categories, services), which helps, but it says nothing about the reference/profiles split, profile_id, observed_at, or the 50-item cap on profiles.

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 names a specific verb ("Vergleicht") and both operands (supplied profile/directory data vs. approved master data), then enumerates the compared fields: name, phones, public address, location URL, hours, areas, categories, services. This makes it unmistakably distinct from siblings such as analyze_web_performance or summarize_local_competitors, which do not diff supplied data against a reference record.

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 clearly states the task context (comparing supplied data against approved master data) and adds explicit exclusions: it does not check the Google profile live, ownership, or the truth of the master data. What is missing is routing guidance to an alternative tool for the live/verification cases it excludes.

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