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

Annotations only declare non-read-only, non-destructive, closed-world; the description adds the material facts an agent actually needs: edits land in a draft only, nothing is public until publish_page, the prompt path is asynchronous and takes a minute or two with a polling contract via my_page, and content is plain text, never HTML. It also discloses partial-update behavior (omitted fields keep draft values), which the annotations cannot express.

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 with the authorization gate and the publish_page boundary, and nearly every clause carries operational content. It is a dense run-on with nested parentheses and an inline example, which costs some scannability without much true padding.

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 nested-object mutation with no output schema, the description covers everything needed to invoke it correctly: auth, mode selection, draft-vs-live state, async completion and polling, content format, field-level constraints, and partial-update semantics. Return values need not be explained since the observable state is described via my_page status.

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 only 50% schema coverage, the description carries real weight: it explains prompt semantics (owner's words, queued, generated from published knowledge) and page semantics (partial update, omitted fields preserved), plus a theme value list the schema does not enumerate. However, several stated limits disagree with the schema (headline 90 vs maxLength 200, intro 400 vs 1000, highlights 4/32 vs maxItems 10/maxLength 100, sections 6 vs maxItems 12, cta 32 vs 100), which could mislead an agent about valid values.

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 ("Change the business page's draft") and immediately scopes it away from the write-to-live sibling by naming publish_page. The two operating modes (prompt vs page) are named up front, so the agent knows exactly which tool and which mode it is choosing.

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 explicit eligibility ("Owners only (needs sign-in)"), an explicit mutual-exclusion rule ("Pass exactly one of prompt or page"), and an explicit follow-up loop (read my_page until status is idle). It also names publish_page as the alternative required to make anything go live, so when-to-use and when-not-to-use are both covered.

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