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

Annotations only declare the safety profile (destructive, non-idempotent, open-world); the description adds behavior an agent cannot get from them: paid AI cost, ~1 minute latency, and the critical warning that a timed-out call can still persist the draft. It also ties persist=false to a preview and autoPublish to immediate publishing, which is essential context for a destructive, non-idempotent tool.

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?

Four tight sentences, front-loaded with the trigger condition and zero filler. The enumeration of return fields is mildly redundant given an output schema exists, but it is brief and sandwiched between higher-value disclosures.

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 7-parameter destructive mutation with an output schema, the description covers triggers, cost, latency, timeout behavior, preview and publish semantics, and exclusions. Remaining gaps (authorization/permission requirements, whether blogId must reference an existing blog) are minor given the schema covers parameters and returns.

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% and every parameter (topic, topicIdeaId, locale, persist, autoPublish, sitemapMaxUrls) is documented in the schema itself. The description only echoes the topic/topicIdeaId choice at a high level, adding no syntax or format detail, so 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?

Names a specific verb and resource ('write a new blog post on a topic or saved topic idea') and scopes it to AI generation rather than manual authoring. The closing exclusion, 'Not for saving your own text,' implicitly separates it from create_article, so an agent can route without opening the schema.

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 a clear trigger ('when someone asks you to write a new blog post') and a when-not ('Not for saving your own text'). It stops short of naming the alternative sibling explicitly, leaving the agent to infer that create_article handles user-supplied text.

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