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

No annotations are provided, so the description carries the full burden, and it does disclose genuinely useful behavior: draft vs published table semantics, public read via /api/agents, and that delete is a permanent hard-delete. However, it omits find-specific behavior such as the default result shape and pagination handling, and much of the disclosure concerns sibling operations (create/update/delete) that this tool cannot perform.

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 text is a sprawling block that dumps the full field list and all 39 layout blocks plus write/publication conventions — content irrelevant to a find tool — with the actual purpose buried after the opening clause. Signal-to-noise is poor and it is not front-loaded around what findPages does.

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 should clarify what a find returns, but it instead documents field schemas and block types for authoring. For a 10-parameter, zero-required query tool it leaves the response shape, pagination, and filtering guidance underexplained while over-explaining sibling concerns.

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%, so the schema already documents all 10 parameters; baseline 3 applies. The description only adds meaning for the draft parameter ('without draft:true returns the published main-table state only') and says nothing about where/select/sort/depth/locale, so it adds marginal value beyond the 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?

The description names the resource ('pages collection', 'Editor-curated marketing pages') but never plainly states that this tool finds/lists pages; it reads as a collection reference dump with 'MCP capabilities: find, create, update, delete' buried mid-way. It does differentiate the resource from siblings like findPosts/findMedia, but the verb for this specific tool is implied rather than stated.

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?

There is some real guidance (call listAvailableBlocks first, use schedulePost for future publishing, use _status='draft' until reviewed), but most of it targets create/update/publish workflows rather than querying pages with this tool. The one find-relevant rule ('a find WITHOUT draft:true returns the published main-table state only') is easy to miss inside the wall of text.

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