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

Annotations already declare readOnly/destructive/idempotent, and the description reinforces the safe profile while adding genuinely new context: the Bridge 1.7.0+ version requirement and the fact that data lives in _crb_* fields rather than post content. It does not cover failure modes (unsupported theme, old Bridge) or output shape in detail, but with annotations carrying safety it earns a 4.

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?

A single dense sentence front-loads what the tool returns, then the theme caveat, then follow-up tools, then the version requirement. Every clause is load-bearing, though the nested parenthetical makes it slower to parse than it needs to be.

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 does the work of describing the return shape (section rows with type and fields, plus single settings), which is what an agent needs before calling. Missing pieces are minor: no statement on empty/non-Carbon-Fields pages and no guidance on the site parameter for a two-param required tool.

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 0%, so the description carries the full burden for 'site' and 'post_id', and it says nothing about either. It does not clarify that post_id is a WordPress post/page ID (not a slug or a Carbon Fields identifier), nor what form the site parameter takes. Only naming convention makes the parameters guessable.

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 (a Carbon Fields page's sections) and states exactly what is returned: each section row with its type and fields plus the page's single settings. The parenthetical about Nomad-style themes storing copy in _crb_* fields rather than post content separates it from wp_get_post. It is a noun phrase rather than a verb-first statement, which keeps it just short of a 5.

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?

Routing is explicit: text edits go to wp_replace_in_post, row-level operations go to wp_carbon_fields_*_row tools, so the agent knows which siblings to pick for follow-up work. It also states the Bridge 1.7.0+ prerequisite. It does not say when to prefer this over wp_get_post or what happens when a page has no Carbon Fields data.

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