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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuine context beyond that: the tool reveals authorization role and whether a working plan exists, and that a planless company is read-only — a behavioral state that affects later mutations. It does not say whether the call errors or returns partial data when no company is associated, which is the remaining gap.

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?

A single sentence front-loaded with the imperative 'Start here:' followed by a scannable list of returned items — no filler or marketing language. The list is dense and slightly run-on, but every clause names a distinct returned field rather than padding.

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?

There is no output schema, so the description must carry the return shape, and it does so by enumerating the field categories an agent will receive. Combined with the plan/read-only caveat, an agent knows both what it gets and what the result implies for subsequent write calls. A note on behavior when unauthenticated or with no company is the only omission.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. Nothing in the text misleads about inputs, and the absence of arguments is implicitly consistent with a 'start here' context fetch.

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 enumerates precisely what the tool surfaces: the current user and role (admin or member), company and careers page, AI-ranking and stage-email flags, plan and AI credits, and saved departments/locations. That is a specific resource definition an agent can distinguish from the CRUD siblings (get_job, list_applications, get_stats). It stops short of a crisp verb phrasing like 'Returns the current account context,' but the content is unambiguous.

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?

'Start here' is an explicit call-order instruction that tells the agent to invoke this before other tools, which is exactly the guidance a bootstrap tool needs. It also flags a prerequisite consequence ('Without a working plan, the company is read-only') that shapes downstream behavior. No alternatives are named, but none of the siblings substitute for this context call.

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