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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the description's added value is the side-effect note "Nothing is sent to the contact" (no notification fired on the person/contact) plus the underlying endpoint. It does not address duplicate-name behavior or what is returned, which matters given idempotentHint=false.

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?

Three telegraphic fragments, front-loaded with the WRITE marker and the core action, with zero padding. "POST /companies" is the least load-bearing part but is short enough not to hurt readability.

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?

The schema fully documents the three inputs and annotations carry the safety profile, so the essentials are covered. However, with no output schema, the description never says what comes back (created id, object shape), which an agent needs after a non-idempotent create.

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 100% — name, user_id (default: the API user) and background are all documented with limits in the schema. The description contributes nothing about parameters, so the baseline 3 is the correct ceiling.

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?

"WRITE: create a company" gives a specific verb plus resource, and the resource noun (company) distinguishes it from create_person, create_deal, create_task and the other create siblings. It stops short of naming an alternative or the boundary with update_company, but the intended action is unambiguous.

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?

There is no when-to-use guidance, no precondition (e.g. whether to check for an existing company via search_companies first), and no named alternative. The WRITE prefix implies a mutation but nothing tells the agent how to choose this over the sibling create/update tools.

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