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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond those: it states 'nothing changes' (reinforcing annotations), clarifies that results are computed from 'latest scan' and 'connected registrar,' and explains what the return payload contains (ops and manualReview with SPF, DKIM, BIMI specifics). It also discloses failure prerequisites (tracked domain, scan exists, registrar coverage), which helps the agent anticipate errors.

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?

The description is tightly structured: the opening verb and resource immediately convey the main purpose, followed by read-only status, return values, and prerequisites. Every sentence contributes meaningful information without repetition or fluff. At three sentences, it is appropriately sized for the tool's complexity.

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 takes on the responsibility of explaining return values, and it does so clearly ('ops' to pass to apply_dns_fix, plus manualReview items). It also covers input context (latest scan, connected registrar) and prerequisites. While it doesn't mention edge cases like when no changes are needed, the level of detail is strong for a single-parameter read-only tool with rich annotations.

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 parameter 'domain' is fully described in the input schema. The tool description adds only that the domain must be 'tracked' and that a scan and registrar connection are required—these are tool-level prerequisites, not new parameter meaning. Since the schema already handles the parameter, the baseline of 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 uses a specific verb ('Compute') and clearly identifies the resource ('exact DNS-record changes needed to fix a tracked domain's deliverability'). It distinguishes itself from siblings by explicitly linking to apply_dns_fix ('pass verbatim to apply_dns_fix') and noting it returns manualReview items, making its preview role unmistakable.

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 context for when to use the tool (previewing changes before applying) and names the alternative (apply_dns_fix) as the destination for the ops. It lists prerequisites (domain tracked, scan exists, registrar connection), which guide the agent's decision. However, it stops short of explicitly saying 'use this instead of apply_dns_fix when you want to preview only,' so the exclusion 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.