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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive). The description adds genuine behavioral specifics beyond them: it reads /sitemap.xml from customDomain, follows a sitemap index one level deep, and returns a bounded sample. However, the stated 'at most 25' cap conflicts with the maxUrls parameter (default 500, max 2000), leaving the actual return bound ambiguous.

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?

Two dense sentences with no filler, and the core action plus traversal depth is front-loaded before the consumer note. It packs a lot into little space, slightly at the cost of the cap ambiguity.

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?

An output schema exists, so return shape needn't be explained, and annotations carry the safety profile; the description covers source, traversal depth, and purpose. The only gap is that it never reconciles its 25-URL sample language with the maxUrls parameter.

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 the schema already documents blogId, locale, and maxUrls, which sets a baseline of 3. But the description introduces 'at most 25 safe sample URLs' while maxUrls permits 500 default and 2000 maximum, injecting contradictory meaning about the cap rather than clarifying it.

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 a specific verb (summarize URLs), a specific resource (the blog's customDomain /sitemap.xml), and even the traversal mechanism (following a sitemap index one level). It is clearly distinguishable from sibling article/blog tools and tells an agent exactly what will be fetched.

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 states the downstream consumer ('Used by generate_article as the allowed internal-link pool'), which implies the primary use case, but gives no explicit when-to-use/when-not guidance relative to alternatives like search_articles or get_article for link sourcing.

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