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

Annotations already declare a safe read (readOnlyHint, idempotentHint, closed-world), so the description's real contribution is the trust caveat: revenue is recorded as sources state it and is unchecked unless evidence is verified. That is exactly the kind of provenance warning an agent needs before repeating numbers. It does not cover pagination or result-count behavior, which keeps it off a 5.

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 purpose then result shape, followed by the evidence disclaimer and sort rule; no filler. The middle clause ("unless its evidence is verified, Horizontal has not checked it") is slightly tangled and takes a second read, which is the only thing holding it back.

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?

Six optional parameters, no output schema, yet the description compensates by describing the result fields (revenue, reporter, evidence strength, agents used, economics, solo-team copyability) and the sort order. It does not address result counts, limits, or paging, which is a modest gap for a search tool with a capped limit of 20.

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 83%, so the structured fields already carry most parameter meaning and the baseline is 3. The description adds one genuinely new piece: ordering is "newest first, or the closest matches first when there are words," which explains how query changes sort behavior. It says nothing about the limit parameter, which has no schema description at all.

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 opens with a specific verb-plus-resource ("Find cases from Horizontal's Agent Cases") and pins the content domain to "real, named people and companies making money with AI agents." It also enumerates what each record contains, which tells the agent the shape of the answer. It stops short of naming the sibling split (search_services / search_trends / get_case), so the boundary is inferred rather than stated.

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?

There is no explicit when-to-use or when-not-to-use statement, and no reference to the sibling get_case or search_services tools that an agent would need to choose between. The only routing hint is implicit: zero required parameters plus "leave it out for the newest cases" implies this is an exploratory browse/search tool. Acceptable but leaves selection to inference.

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