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

Annotations already mark readOnly, idempotent, and non-destructive, but the description adds substantial behavioral detail beyond that: dedup by company, geo resolution with explicit unresolvable-country errors instead of partial pages, bounded limit, per-company billing, empty results billing nothing, and demo-mode/signup-link behavior. No contradiction with annotations.

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?

The description is long but information-dense and front-loaded with the key decision ('WHEN an agent needs to FIND...'). Every sentence adds a distinct fact: matching scope, error behavior, pagination, billing, demo mode, and sibling routing. The examples at the end illustrate behavior without redundant repetition.

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?

For a complex tool with no output schema, the description covers invocation context, parameter semantics, error handling, pagination, billing, demo credentials, and sibling routing. Minor gaps remain: `idempotency_key` semantics are not described, the behavior when both `role` and `geo` are omitted is unclear, and the API-key guidance conflicts with the schema's deprecation note. Overall, it is strong but not fully complete.

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?

With only 14% schema description coverage, the description compensates well for `role` (free text matched against posting title, not an id), `geo` (resolved to a stored country, unresolvable values error), `limit` (bounded), `cursor` (keyset pagination), and `plane_api_key` (demo behavior). However, `idempotency_key` is not explained, and the `plane_api_key` guidance conflicts with the schema's deprecation note, so it is not a 5.

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 opening states exactly what the agent is doing: 'FIND the companies worth working' and describes a 'Reverse who's-hiring-for {role, geo} search.' It clearly distinguishes itself from the sibling `is_hiring` by explicitly routing yes/no lookups there, and from keyed company lookup. The verb, resource, and search direction are all specific.

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?

The description explicitly frames when to use it: 'the sourcing step, before it knows which companies exist.' It also gives a direct alternative rule: 'Already holding a company_id and only need a yes/no? Use `is_hiring`.' It further instructs agents to page with `cursor` rather than raising `limit`, which is practical usage guidance.

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