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

Annotations already provide idempotentHint=true, readOnlyHint=false, and destructiveHint=false, but the description adds critical behavioral detail: 'Only the fields you provide are changed; omitted fields keep their current values.' This reveals partial-update semantics that annotations cannot express. It also states the return value ('Returns the updated record') and prerequisites for recordId, adding value beyond the structured fields.

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 tightly packed sentences: the first states the operation, the second covers authentication and update semantics, the third covers the data dependency and return value. Every sentence earns its place, and the most important action verb appears immediately at the start.

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?

For an 8-parameter tool with no output schema, the description plus the fully self-documenting schema cover everything an agent needs: what to call, prerequisites (authentication, recordId from listDnsRecords), partial-update behavior, and the return shape. The annotations fill in idempotency and non-destructiveness, making the entry complete.

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% for all 8 parameters, so the baseline is 3. The description goes beyond the schema by explaining the partial-update model: provided fields are changed and omitted fields retain values, which affects how an agent should build the request. It also orients the agent to source recordId from listDnsRecords, adding practical meaning to that parameter.

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 opens with 'Update an existing DNS record', a specific verb+resource pair that clearly distinguishes this from createDnsRecord, deleteDnsRecord, getDnsRecord, and listDnsRecords. The word 'existing' reinforces that this is a modification tool, not a creation tool.

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 description provides clear operational context: it requires authentication, performs partial updates (only provided fields change), and tells the agent to obtain recordId from listDnsRecords. It stops short of explicitly naming when not to use it (e.g., 'use createDnsRecord for new records'), so it lacks a formal exclusion but is still unambiguous.

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