search-site-pages

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

With readOnlyHint already covering the safety profile, the description adds real behavioral context: it spells out the return shape (Matched/Returned/Truncated/Root/SiteName/Pages) and the page-addressability rule, which prevents agents from assuming template-name heuristics. It stops short of stating permission requirements, performance characteristics, or how the default 500-row cap interacts with large sites.

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?

Three sentences, front-loaded with the verb+match semantics, then the return shape, then the page definition. Dense but every clause carries information; the page-definition sentence could arguably be trimmed but it earns its place by preventing false negatives/positives from template-name guessing.

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?

Despite no output schema, the description documents the return envelope including truncation fields, and the schema covers all six parameters with defaults and the path/siteName either-or. The main gap is routing guidance against the many sibling search and page-listing tools, which is left to the agent to infer.

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 baseline is 3, but the description genuinely adds semantics the schema does not: the query is case-insensitive and substring-based, and it enumerates the four fields searched. That is meaningful matching behavior an agent cannot derive from the parameter schema alone.

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 (search a site's pages) and pins down the matching semantics (case-insensitive, substring, against Name/display name/Title/NavigationTitle). The explicit definition of what qualifies as a 'page' (has a layout, directly or via template standard values) separates it from generic item-search siblings like item-service-search-items and authoring-search.

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?

Usage is implied rather than stated: the tool is site-scoped and page-only, and parameters reference 'list-sites' for site names, so an agent can infer it should use this instead of full-tree item search. But there is no explicit when-to-use/when-not, no named alternative (e.g. get-pages-by-site, item-service-search-items), and no statement that path or siteName is required to resolve the site at call time.

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