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

Goes well beyond the destructiveHint=true annotation by disclosing exactly what gets destroyed/cleared (empty strings clear text, false disables toggles, [] clears lists, arrays replace whole lists) and by documenting version-conflict reconciliation and idempotency-key reuse rules. It also clarifies that saving does not publish the site, an important side-effect boundary.

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?

Front-loaded purpose and sectioned Args make it easy to scan, and the long field enumeration is justified by the empty schema. It is on the dense side, but nearly every line earns its place; only minor tightening is possible.

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 complex mutation tool with a nested, undocumented settings object, the description covers the read-then-write workflow, field semantics, versioning/idempotency, clearing rules, and the fact that saving does not publish. Return values are covered by the output schema, so no gap remains.

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?

With 0% schema description coverage and a free-form nested settings object (additionalProperties: true), the description carries the full burden and delivers: it enumerates every editable field by group, gives value formats (HH:mm, 0..1), and explains ai_mutation_version/idempotency_key conditional requirements. This is exceptional compensation for an opaque schema.

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 (Patch) and resource (existing platform SEO settings) plus a key semantic ('omitted keys remain unchanged'). It also names the sibling get_seo_settings, so an agent can immediately distinguish read vs. write in the SEO pair.

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?

Explicit workflow: read get_seo_settings first, send only changed editable_fields, and use this instead of duplicating JSON-LD in source. This is a clear when-to-use with a named alternative and a stated anti-pattern, leaving nothing to inference.

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