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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: the YAML serialization format, the per-node field set, the caveat that nodeIds are only unique within a project/publication, and that publication TOCs are read-only auto-generated copies. It does not discuss response size limits or failure behavior for invalid parentId.

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?

Front-loaded with what the tool returns, then usage, then scoping advice, then caveats — a logical order with no filler. Minor redundancy between 'Returns hierarchical TOC tree as YAML' and the later 'Returns: title, topicId, nodeId, visibility', but the second sentence adds field detail rather than repeating.

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, the description carries the return-value burden and does so by enumerating per-node fields, which is the key omission it needed to cover. Combined with the nodeId uniqueness caveat and the read-only publication note, an agent has enough to call it correctly; only edge cases such as invalid parentId handling or very large responses remain unaddressed.

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 100%, so all four parameters are already documented in the schema, making 3 the baseline. The description adds practical meaning for two of them by explaining why to use parentId (scope to a subtree) and maxDepth (limit depth on large projects), but says nothing extra about includeHidden or how projectId differs between projects and publications beyond the schema text.

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 ('Returns hierarchical TOC tree as YAML') plus the concrete goals it serves: exploring structure, finding nodeIds, understanding parent-child relationships. It does not explicitly distinguish itself from siblings like get_child_toc_nodes, get_toc_node, or find_toc_nodes, so an agent must infer the boundary between a full-tree fetch and a single-node or search call.

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?

Gives clear situational guidance ('use this to explore project structure, find nodeIds, or understand parent-child relationships') and practical scoping advice for large projects via parentId and maxDepth. It stops short of naming alternatives or stating when not to use it (e.g., when a single node or a search would be cheaper), leaving that inference to the agent.

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