Get Space Page Tree

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful return-shape context (parent_id/depth attributes, token-efficient flat list versus ASCII trees), but says nothing about pagination behavior or what happens past the limit, and its phantom filter claims muddy the picture.

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?

The opening sentence is well front-loaded and the closing 'use this to...' is efficient. The middle sentence, however, spends its words on depth/title filters that the tool cannot perform, so a full sentence of the description does not earn its place.

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 rich annotations and an output schema present, the description need not explain return values or safety, and it does convey the flat-list hierarchy structure well. It is still incomplete on pagination (limit caps at 1000) and on how it differs from confluence_get_page_children, while including misleading filter claims.

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 two real parameters are documented (limit as 'Max pages to fetch', space_key as 'Space key'). The description instead describes depth and title filtering that do not exist in the schema, actively misleading the agent about what it may pass. This is a net negative over the baseline of 3.

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 ('Get page hierarchy for a Confluence space') and immediately clarifies the output shape ('as a flat list' with parent_id and depth). It does not name the closest sibling (confluence_get_page_children), so an agent must infer the space-wide vs single-page scope distinction itself.

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?

'Use this to understand space organization before creating/moving pages' gives one concrete usage context. However, the guidance to 'filter by depth' and 'find pages by title' points at capabilities the tool does not expose, which is worse than no guidance because it invites invalid invocation attempts.

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