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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add beyond that. It does: privacy ("Only the address leaves JOBFLOW, nothing personal"), cost ("Free"), and geographic coverage limits. It does not cover rate limits or failure behavior, but the added traits are genuinely useful.

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-loads the core mapping ("Address to building") and has no filler sentences, but the middle clause leans on JOBFLOW-internal jargon ("Tresor", "building memory") and the use-case list is a touch ornate for the space it takes.

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 no output schema, the description helpfully enumerates the returned fields, and it covers scope (Swiss register), privacy and cost. The only real gap is the two undocumented input parameters, which the description leaves to the schema.

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 33% – only address is documented, and city/postal_code are bare. The description does not clarify the relationship between address, city and postal_code or how they combine, so it fails to compensate for the coverage gap (the address example lives in the schema, not here).

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+resource (address to building) and enumerates the returned fields (EGID, parcel, E-GRID, year built, floors, flats, heating, coordinates), which is unusually informative. It does not differentiate from potential siblings like search or fetch, so it stops 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?

Gives clear context for when to reach for it ("The start for any work on a building: a quote, a guarantee in the Tresor, building memory, finding owners") and a hard constraint ("Switzerland today; elsewhere it answers none"). It never names an alternative tool or an explicit when-not case beyond the geography limit.

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