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

With no annotations, the description carries the load and does add real behavioral context: the refusal condition when Yoast is inactive, the fact that unknown or empty template variables are removed from output, and the exactly-one-scope constraint. It stops short of stating auth/permission needs, whether omitted fields are preserved or cleared on partial updates, or how the mutation takes effect.

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?

Dense but front-loaded: the scope constraint and its three values lead, followed by per-scope enumerations, then variable syntax, then the refusal rule. Parenthetical detail is heavy but every clause carries information an agent needs, and nothing is redundant with the schema.

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 a 24-param mutation tool with no annotations, the description supplies the scope model, refusal precondition, variable semantics, and a pointer to the seo-contract skill doc; an output schema exists so return values need not be explained. It is only incomplete in not documenting several individual parameters and in not clarifying preservation/replacement semantics for omitted fields.

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 only 17% across 24 params, so the description must compensate, and it does so well by grouping parameters under their scope (postType: title/metaDesc templates, noindex, schema types; site: separator, website name, knowledge graph fields, defaultOgImageId, home templates) and explaining the %%...%% variable syntax. Gaps remain for ungrouped params such as socialTitle, socialDescription, alternateName, personUserId, breadcrumbsEnabled and the schema page/article types.

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 ('Set Yoast DEFAULTS') and enumerates the three mutually exclusive scopes it operates on (postType, taxonomy, site:true) with the concrete fields each covers. It also distinguishes itself from siblings by noting the archive variant is set-seo and that the scope must be exactly one, so an agent can tell it apart from set-seo/list-seo without opening schemas.

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?

Gives clear operating context: exactly one scope per call, an explicit precondition ('Refused when Yoast is not active'), and a mandatory first step ('get-skill-doc {id:"seo-contract"} — read it before the first call'). It routes the archive case to set-seo, but does not contrast with set-seo for individual posts or with get-seo beyond that single mention.

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