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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add behavior — and it does: result ordering ('top-level paths first and then by path'), the short-row shape, the three access values with a gloss for private_link, and full pagination semantics including the ~6,000-token reply budget, total, hasMore, and nextCursor reuse. This is context an agent could not derive from the annotations.

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?

Usage is correctly front-loaded, and the per-parameter bullets make scanning easy. Some sentences do not earn their place: the multilingual keyword parenthetical, the closing 'Read-only.' that merely repeats the annotation, and the cryptic rule 'Link a public page only from a page anyone can read.'

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?

Filters, pagination, ordering, result row shape, and the no-page-means-create handoff are all covered, and an output schema exists so return data need not be explained at length. For a five-parameter read tool with full annotation coverage, nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so 3 is the floor, but the description goes beyond it: it explains that omitting host dedupes pages to the site of their main URL, and gives the trailing-slash distinction for pathPrefix ('/guides/' lists under /guides/; '/guides' also includes /guides itself). The limit/token interaction and the cursor loop are also stated operationally rather than restated.

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 opening sentence pins down the verb, resource, and the retrieval axis ('the workspace's pages by URL'), and the second sentence spells out exactly what is returned (id/siteId, name, path, status, url, access) plus result ordering. An agent can tell this apart from list_sites, get_page_structure, and create_page without opening any 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?

It gives concrete triggering scenarios ('every page under /guides/', 'pages on www.example.com', 'the ones not live yet') and explicitly routes the create case to create_page ('A path that isn't listed has no page: create_page makes one there'). It never explains why to prefer this over siblings like get_page_structure or list_sites, so the exclusion side of the guidance is incomplete.

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