Get a document

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

Annotations declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is already covered, and the description adds substantial complementary behavior: relations are returned in both directions but stored only on one side (so relations.inbound alone recovers a person's parents), the body contains content available nowhere else, numbered paths disambiguate duplicate names, and collection paths return collection contents. This genuinely recounts traversal semantics the annotations cannot convey, with zero contradiction.

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 description is long, but nearly every line earns its place: the path catalog is actionable, the inbound-direction paragraph explains a genuinely hidden gotcha, the body sentence prevents a common mistake, and the disambiguation sentence routes to search_concepts. The opening line front-loads the core purpose before any detail, giving a well-ordered, efficient structure despite its length.

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 an output schema present, the description correctly avoids re-documenting return fields and instead fills the gaps: edge cases (duplicate names), a domain-specific data model quirk (one-side-only relation storage), body-attribution semantics, and collection-style paths. For a graph/document retrieval tool of this complexity, there is no mission-critical information an agent needs that is missing.

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% for the 3 parameters, so the baseline is 3, but the description adds real semantic value for `path` — concretisized path examples, numbering rule, and collection-path behavior — and for `body`, explaining what kind of content lives in the prose and why one would request it. The reason for the backlinks parameter, by contrast, is already fully captured in the schema. The added semantics justify a 4.

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 uses a specific verb ('Fetch') plus a clear resource ('any document in the knowledge base by path') and then disambiguates that scope with 12 concrete path patterns spanning People, Places, Themes, Lexemes, and more. It actively differentiates itself from siblings by naming search_concepts as the alternative for resolving ambiguous paths. This makes the tool's role unmistakable relative to get_passage, search_scripture, and list_documents.

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 explicit routing guidance: use search_consensus-like search_concepts first when a path might be ambiguous, set body=true when the target prose (Strong's definitions, Hebrew, outlines) is needed, and expect collection paths to behave differently. It clearly states the precondition for correct use (the/numbered path) but does not enumerate exclusions for every sibling tool.

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