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

Annotations already cover readOnly/idempotent/openWorld, but the description adds substantive behavior: no phone numbers returned, opted-out people excluded entirely, addresses never synthesized from a name@domain template, no SMTP probing because domains are mostly catch-all, and per-address worth labels (company inbox, shared short address, former job, private mailbox). That is exactly the operational context an agent needs before trusting results.

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 most decision-critical constraint (admin-only, do not offer for customer accounts) is front-loaded, and every paragraph carries payload. There is mild redundancy in the sibling routing, which is stated once early and restated later as "This is the roster layer," so it is dense and useful rather than perfectly tight.

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, yet the description fully specifies what comes back — named team rows with role/grade/seniority/country/LinkedIn plus addresses annotated with their worth — and states the important negatives (no phones, opted-out excluded). For a read-only enrichment tool of this complexity, nothing consequential is left for the agent to guess.

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 the baseline is 3, but the description adds real meaning: it explains that top limits named rows while metrics still describe the whole team, and supplies a concrete roles usage pattern (founder,ceo to keep only cold-email responders). It does not add much beyond the schema for the contacts toggle, keeping it short of 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 description opens with a specific verb+resource: "Get the people of a company and the addresses to reach them," then names the exact inputs (domain, LinkedIn slug, or name) and the exact output fields (name, role, grade, seniority, country, LinkedIn, labelled addresses). It also explicitly segments itself from siblings: company_signals profiles the ACCOUNT, person_signals explains ONE human, analyze_contact scores the deal. An agent can route correctly without opening any other schema.

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?

It gives both when-to-use ("Use after company_signals, when the account is worth working") and when-not-to-use ("the upstream refuses this tool for customer accounts, so do not offer it as an option") with named alternatives in each case. It even routes to email_intel for the specific case where a single address must be trusted, and specifies roles=founder,ceo for cold-email targeting.

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