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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds the response envelope and the next_skip paging loop, which is real behavioral context. It does not say how filters and query combine when both are supplied, nor how large the collection is, but for a read-only list tool this is solid.

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?

Four short sentences, each carrying distinct information — resource identity, return shape, paging, then filtering — with the identity and response shape front-loaded. The trailing "GET /companies." is nearly free but is the one clause that does no work for an agent choosing a 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?

With no output schema, the description correctly supplies the return envelope { count, next_skip, items } and the continuation rule, which is the main thing an agent cannot infer. Six optional parameters are all schema-documented, so the remaining gap is only interaction behavior when multiple filter inputs are combined.

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 100%, so every parameter is already documented, and the description mostly restates it — "pass next_skip as skip" and "filter with exact-match fields or a MongoDB-style query" mirror the schema's own wording for skip, filters, and query. It adds no format or precedence detail beyond the schema, so the 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?

Names the resource and disambiguates it domain-wise with "clients that group people," which separates it from the many create_* siblings and from list_people. The list semantics come from the sibling-name pattern and from "Returns { count, next_skip, items }", but the description never says outright "lists companies" — it leads with a noun definition.

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 concrete routing: "Pass id to read one record" (single-record fetch instead of a filtered list), the paging contract, and a choice between exact-match filters and a MongoDB-style query. It stops short of stating when to prefer filters over query, or when to reach for a different list tool.

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