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

Annotations already carry readOnly/idempotent/non-destructive, so the description's added value is mostly the ID-semantics warning and the per-source counts in the response. It adds useful context but does not disclose pagination behavior, ordering, or how counts are keyed.

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?

Three tight, front-loaded sentences with no filler; the purpose leads and the filter caveat follows. The final sentence concerns a sibling tool, which is useful routing but slightly outside the tool's own scope.

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?

Complete enough for a three-parameter, zero-required list tool that has both annotations and an output schema. Return shape is delegated to the output schema, and the only remaining gap is pagination/ordering behavior.

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 baseline is 3, but the description adds genuine meaning beyond the schema by warning that source_company_id is a company.id from following.list, not a follow ID — a distinction the schema's 'Company ID of a followed company' does not make.

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 (discover companies recommended from companies you follow) and implicitly distinguishes itself from recommendations.get and following.list by naming what it returns: one flat list plus per-source counts.

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 routing guidance for two adjacent tasks: use following.list to obtain the company.id for source_company_id, and use following.follow with candidate_company.id to act on a recommendation. It stops short of saying when to prefer recommendations.get over this list tool, but the context is explicit.

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