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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds above that: per-profile credit cost and, importantly, the eventual-consistency caveat that an unread company returns as 'building' and is populated in the background — a real trap the agent is warned about. It does not cover partial failures or what happens to unresolvable identifiers.

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?

Front-loads what is returned, then input shape, then cost, then the freshness caveat — a sensible order with no filler sentences. Slightly dense, with a mid-sentence parenthetical stance list that trails off into '...', but nothing is wasted.

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 carries the burden of describing the return payload, and it does enumerate the output facets plus cost and staleness behavior. The stance vocabulary is left open-ended and the response shape (per-company object vs keyed map) is not stated, but the essential call-ability information is present.

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% and the single `companies` parameter already documents domain, LinkedIn URL, id, and name plus the 25-item cap. The description restates those same identifier forms and the cap without adding syntax, normalization, or batching guidance, so the baseline of 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?

States a specific verb and resource — 'Return each company's hiring picture right now' — and enumerates the returned facets (open roles by family/function, leadership and founding roles, tools, hiring stance, 90-day signals). An agent knows exactly what it gets. It never differentiates itself from the sibling `hiring_signals` tool, which covers overlapping 'hiring signals' territory, so selection between the two still requires a guess.

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 invocation context: batch up to 25 companies, accepted identifier forms, and one credit per returned profile — enough for an agent to judge cost before calling. It stops short of naming when to prefer this over `hiring_signals`, `company_timeline`, or `companies`, and states no exclusions.

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