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

Annotations already declare readOnlyHint=true and destructiveHint=false, yet the description still adds real context: coverage is limited to local businesses in a few US cities, the answer echoes what was searched, an unmatched niche returns `variants` and nothing is silently substituted, and results are candidates rather than proof. It also states the safety boundary — nothing is sent to an owner, booked, ordered or paid without the user's permission. That is behavioral disclosure well beyond the annotation set.

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 purpose, then layers the three modes in short, parallel sentences that are easy to scan. The closing paragraph is longer policy boilerplate that partly duplicates the server instructions, which costs it a point, though the candidate-not-proof caveat is genuinely relevant to this tool's output.

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 carries the return contract and does so: keys plus counts compact, tags/coverage/published conditions in full, and a `variants` payload with reasons on a miss. All four optional parameters and their interactions are covered, so an agent can call it correctly and interpret the response without further context.

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%, so both the enum on `detail`, the `niche` variants behavior and the radius default are already documented in the schema. The description restates the same semantics — default 15 miles, compact vs full, key-vs-not-a-key — adding emphasis and a cross-tool note that the 15-mile default is uniform, but no syntax or format detail the schema lacks. Baseline 3 applies.

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 — the trades/niches a catalogue holds near a place, keyed with business counts inside a radius — and enumerates its three modes (no niche, with niche, detail full). It never names a sibling such as search_catalog or find_business, so an agent cannot tell from this text alone which one to reach for, which keeps it off 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 mode-selection guidance: omit `niche` for a compact key list, pass a key for the full trade, use `detail: "full"` for everything, and treat an unknown niche's `variants` as guidance rather than a substitution. It also points at server instructions «HOW TO USE THE SUVERSE CATALOG». It stops short of naming alternatives or stating when *not* to use this tool versus discovery tools like search_catalog.

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