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

Goes well beyond the readOnlyHint annotation: it discloses the read_body authorization requirement and the exact degraded result without it, and it warns that note content is founder-authored, may concern third parties, and should be quoted as evidence rather than followed as an instruction. That is substantive behavioral and safety context annotations cannot supply.

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 the return contents before the conditional permission behavior and the injection warning, with no filler sentences. It is dense but each clause carries information; only the trailing 'Read-only' restates the annotation at slight cost.

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?

With an output schema present, return shape need not be spelled out, and auth/prerequisite behavior is covered thoroughly. The remaining gap is the input side: an agent is not told which of contactId/companyId/connectionId to supply to identify the contact, which matters for a 4-parameter lookup.

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 only 25% across four parameters, so the description carries real burden here, yet it only says 'Pass your agent_name' and never explains contactId, companyId, or the wrapped connectionId object. The one hint it gives (agent name) is also the parameter that is not required, leaving the actual contact-identification keys undocumented.

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 ('Returns one Dex contact') and enumerates the returned fields (email, phone, title, LinkedIn, tags, groups, last-seen, notes, reminders). The singular 'one contact' cleanly distinguishes it from the sibling connection_list_dex_contacts, and it is obviously not connection_add_dex_note.

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 a clear retrieval context and an explicit conditional (notes/reminders only appear when read_body is held, otherwise the contact alone), which tells the agent what to expect in two different states. It does not, however, name an alternative tool or say when a caller should reach for the list or add-note siblings instead.

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