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

Annotations carry destructiveHint=true, so the description need not restate mutation risk, yet it adds real value: the 'MUTATES' signal, the read-only restriction on Auto Increment/Formula/Equation fields, and the fact that it returns the created record. It stops short of disclosing validation failure behavior or side effects on linked objects.

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, front-loaded with the 'MUTATES' signal and the core action. The endpoint detail is borderline but useful for disambiguation; nothing is padding.

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 no output schema, the description compensates by noting it 'Returns the created record', and it covers the read-only-field constraint. It could say more about objectKey sourcing or required permissions, but an agent has enough to call it correctly.

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%, so the schema already documents both objectKey and fields. The description restates the fields example verbatim rather than adding syntax or edge-case guidance beyond the schema, so baseline 3 applies.

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?

The description states a specific verb+resource ('creates a new record in an object') and even names the underlying endpoint POST /objects/{object_key}/records. This clearly distinguishes it from siblings like knack_update_record and knack_delete_record 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?

The 'MUTATES Knack data' framing and the create verb imply when to use it, but no explicit condition for choosing this over knack_update_record or knack_request is given. Usage is implied rather than stated.

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