conf_get_children

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the entire safety profile is provided structurally and the description restates none of it. The description contributes no behavior of its own: nothing about pagination defaults, whether children are recursively expanded or direct-only, ordering, or what happens for an invalid or inaccessible pageId.

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?

At five words there is no waste and the purpose is front-loaded, so it is not poorly structured. The problem is under-specification rather than verbosity: brevity here costs clarity instead of buying it, so it does not merit a high conciseness score.

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, no annotation-independent detail, and 0% schema description coverage over limit/start, the definition is too thin for the tool's actual surface. An agent cannot tell whether children are direct-only or recursive, how pagination terminates, or how to interpret an empty result, all of which matter for correct invocation.

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% across three parameters, so the description is the only place semantics could be added and it adds very little. '(one page)' weakly signals that pageId identifies a single parent, but limit and start are never mentioned, leaving pagination behavior entirely undocumented. The gaps are real but the parameter names are largely self-explanatory, keeping this at a minimum-viable 3 rather than lower.

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 verb+resource ('List child pages') is identifiable, and '(one page)' hints the result is scoped to a single parent rather than the whole space, which loosely separates it from conf_search and conf_get_page. But the phrasing is compressed to the point of ambiguity: it never names the parent page or says what a 'child page' is in this hierarchy, so an agent must infer the semantics from the parameter name alone.

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 no when-to-use guidance and no reference to any of the many plausible alternatives (conf_get_page for a single page, conf_search for lookup, conf_get_spaces for hierarchy). An agent must decide for itself when child-listing beats a direct page fetch, with nothing in the description to arbitrate.

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