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

The only annotation is destructiveHint=true, so the description carries most of the burden — and it delivers: it flags the mutation ('MUTATES Codat data'), states the resulting PendingAuth lifecycle state, and explains that authorization happens outside the tool via the returned linkUrl. It omits permission/scope requirements and failure behavior.

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?

Four tight sentences with zero filler, front-loaded with the mutation warning and followed by the required inputs, the resulting lifecycle state, and the API mapping. Every sentence earns its place.

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, and the description compensates by stating that the created connection is returned and that linkUrl is the field the caller needs. Combined with the PendingAuth state disclosure, this is complete enough to call correctly, though error or duplicate-connection behavior is unaddressed.

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 already 100%, so the baseline is 3, but the description adds real value by giving a concrete platformKey example ('gbol' for QuickBooks Online sandbox) and re-emphasizing the source of that value. The 'fields' escape hatch is left to the schema.

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 ('create a new data connection on a company for a given source platform'), plus the underlying endpoint POST /companies/{companyId}/connections. It is clearly distinguishable from the read-side siblings codat_get_connection and codat_list_connections.

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?

It routes the agent to the prerequisite tool explicitly ('platformKey from codat_list_integrations') and explains the downstream flow (customer completes authorization via linkUrl). It does not, however, contrast when to use this versus codat_get_connection or how to recover if a connection already exists.

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