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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description layers on non-obvious behavior well beyond them: quota consumption, that it resolves dead addresses to the current employer, the deliberate asymmetry where an email query returns no name or slug while a URL/slug query does, and the match_confidence / linked_profiles ambiguity path. That is exactly the operational context annotations cannot express.

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 the identity thesis, then cost, then sibling routing, then output caveats — a sensible order. It is dense rather than padded, but a few clauses restate the same rule (the email-vs-URL privacy point is made twice) and could be tightened without losing information.

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 single-parameter tool with no output schema, the description carries the full burden and does so: it enumerates the returned facets, discloses cost, explains identity resolution on dead addresses, and tells the agent how to report low-confidence matches. Nothing needed to call it or interpret results is missing.

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% for the single parameter, so the baseline would be 3, but the description adds meaning the schema does not: the input type changes the answer (email queries strip identity, URL/slug queries return the name because the caller already holds it). It also states the dead-address fallback behavior, which is genuine semantic value for the one parameter.

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?

"Who a person is and what is going on with them" is followed by an explicit inventory of what comes back (role, grade, company, trajectory, published subjects, reading habits, self-reported status, verdict). It then positions itself against siblings by name — email_intel answers whether the ADDRESS is usable, analyze_contact scores the DEAL, this one says who the human is — so an agent can discriminate without opening any 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?

Gives both the trigger and an explicit exclusion: "reach for it when you need the human behind the address, not as a warm-up before analyze_contact." It names the two adjacent tools and states the division of labour, plus the cost condition (one quota request per contact) that governs whether to call it at all.

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