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

Annotations already declare the write/destructive/open-world profile, and the description adds real value on top: an upfront domain dedupe check, default field settings and default tags applied automatically, and consumption of one lookup credit when details aren't cached. It stops short of explaining what happens when a duplicate is found (overwrite, skip, or require confirmation), which matters given destructiveHint=true.

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?

Two sentences, front-loaded with what the tool does, then behavior and cost. Every clause carries information the agent needs; no filler or repetition of the title.

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 values need no explanation, and the credit cost, dedupe step, and default enrichment are covered. The remaining gap is the duplicate-resolution path and the fact that no parameter is required, which leaves the agent guessing what to supply and what happens on a match.

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; the description goes further by framing domain and profile_url as alternative sources of identification and clarifying that the tags argument is additive to the customer's defaults. It does not address what happens if neither identifier is supplied, despite zero required parameters.

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 ('Add a company to the customer's connected CRM') plus the two accepted inputs, which cleanly separates it from siblings like add_person_to_crm, search_companies, and find_company_details. An agent can identify the operation 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?

Usage is implied by the mutation verb and the note that it checks the CRM for the same domain first, which hints it handles dedupe itself. However, it never says when to prefer this over find_company_details + update_crm_record, or when a duplicate should be routed to confirm_possible_match instead. No explicit exclusions are given.

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