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

Annotations already indicate readOnly, idempotent, non-destructive, and open-world behavior. The description goes well beyond these by stating that nothing is looked up or stored, that invalid inputs are refused with an error, that SPF has a ten-term evaluation limit, and that nested lookups can alter the count. This is rich behavioral context with no contradiction.

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 long but every sentence carries useful information: purpose, parameter guidance, limits, alternatives, error behavior, and side-effect guarantees. It is front-loaded with the core purpose and then layers details logically. A slight deduction because it is dense enough that an agent may need to parse carefully, but there is no fluff.

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 burden of explaining return values, and it does: 'Returns the record, direct lookup count, whether that direct count or the 255-character limit is exceeded, plain-language warnings, and the DNS entry to publish.' It also covers error cases, parameter meaning, and sibling tool routing. Nothing critical is missing for correct invocation.

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%, so the baseline is 3. The description adds meaningful domain knowledge beyond the schema: concrete include values like '_spf.google.com' and 'spf.protection.outlook.com', the policy meanings of '-all' and '+all', and the warning that '+all' should never be published. This justifies a score above baseline.

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 a specific verb and resource: 'Build an SPF (Sender Policy Framework) record — the DNS TXT record that lists which servers may send mail for a domain.' It clearly differentiates from siblings like check_spf and flatten_spf by naming them explicitly. This is far more than a tautology.

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 gives explicit usage guidance: 'Use check_spf to resolve and validate a live record, and flatten_spf only when an existing record is over the limit.' It also clarifies that this tool is a pure builder and that validation with check_spf is recommended. The when/when-not distinction is unmistakable.

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