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

Annotations only declare readOnly and open-world, but the description adds substantial behavior: return contents (primary number in international form, line type, country, all other usable numbers), 30–90 second latency, an is_retriable signal with same-input retry semantics that avoids a duplicate search, and a billing model that charges full price for a mobile and 1 credit for office/VoIP only. It even flags the legal responsibility for unsolicited calls, which no structured field conveys.

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-loaded with what is returned and what it costs, then alternatives, then latency/retry, then inputs and price. Dense but almost every sentence carries operational weight; the cost is mentioned twice ("Charged only for a number found" and "Cost: 87 credits"), which is mild redundancy rather than waste.

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, but the description describes the returned fields, the retry path for incomplete searches, and the cost model, so an agent can call it and interpret the result without guessing. Nothing material is missing for a 5-parameter, zero-required lookup tool.

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 routing meaning the terse schema labels do not: linkedin_url yields the most matches, and name-based searches need a domain or company qualifier. It stops short of stating whether the qualifier is strictly required or how results degrade without it.

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?

"Find a person's direct phone numbers" gives a specific verb and resource, and the description immediately contrasts with siblings (emails for work email, profiles for identity). An agent can distinguish this from every other lookup tool without opening the 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?

Explicit when-to-use ("Use to reach a named person by phone") plus named alternatives for adjacent needs (emails, profiles). It also tells the agent which input shapes to prefer: "Pass linkedin_url (finds the most), or first_name and last_name with domain or company."

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