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

Beyond already-strong annotations (readOnly, idempotent), the description reveals genuinely non-obvious behavior: relations are stored only on one side, so inbound relations must be requested explicitly; body content exists only when body=true; collection paths return collection contents. It even explains the path layout for the ambiguous corpus. This is real behavioral value above and beyond the structured fields.

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?

Despite covering many path types and edge cases, the description remains well-structured and purposeful. The path examples are front-loaded, the behaviors are clearly separated, and no sentence is filler. The length is justified by the breadth of document types the tool must address.

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?

This description is remarkably complete for a path-based fetch tool. Together with full parameter schema coverage, strong readOnly/idempotent annotations, and an output schema, the description already handles path disambiguation, collection behavior, body requirements, relation-direction semantics, and alternative routes when the path is uncertain. Little is left for the agent to guess.

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 already strong. The description adds additional semantic meaning for path: an extensive set of valid path prefixes, the fact that a collection path returns whatever that collection holds, and meaningful examples of when body=true is required for prose that is not available elsewhere. It does not deepen the meaning of backlinks much, but the schema description already handles that well.

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 opens with a clear, specific verb and resource: 'Fetch any document in the knowledge base by path.' It then enumerates the exact path categories it covers and states exactly what is returned (structured fields, relations in both directions, links, optional body). It also distinguishes itself from one sibling by routing ambiguous lookups to search_concepts.

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?

The description gives clear context on when this tool fits — fetching path-based documents, collections, and documents with prose — and explicitly recommends search_concepts first when paths are ambiguous. It lacks explicit exclusions or direct comparisons with other sibling tools like get_graph_neighborhood or get_family, so it falls just short of a 5.

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