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

Annotations only say readOnly/idempotent/openWorld; the description goes well beyond them by explaining edge orientation (parent to child with view identity retained), cursor continuation semantics including re-fetch and rejection of changed topology, that empty relations succeed while upstream failures error, and that node names may lag live IDs. These are non-obvious behaviors an agent could not infer from 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?

Purpose leads, then discovery, then parameter rules, then edge/pagination semantics, then error and freshness caveats – a sensible ordering with no filler. The telegraphic clauses about topology rejection and catalog lag are dense but each carries real information rather than padding.

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 six parameters, an output schema, and full annotation coverage, the description supplies exactly the missing behavioral layer: pagination, error/success distinctions, and catalog staleness. Nothing needed to call the tool correctly is absent.

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% and already documents id format, limit caps, cursor opacity, viewId default/all, and primaryOnly's restriction, so the description's viewId/primaryOnly notes largely restate the schema. Only the cursor follow-next and default-view framing add slight value, so the baseline 3 applies.

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 first sentence gives a specific verb (navigate) plus resource (CWE hierarchy) and enumerates the four relation types, so an agent immediately knows this is traversal, not lookup. It explicitly routes ID discovery to cwe_search_weaknesses and cwe_list_reference, separating it from the get_* siblings that return a single node.

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?

It states how to obtain IDs, what the default view is (1000), how to span all views (viewId all), and that primaryOnly is valid only for ancestors. What it doesn't do is contrast traversal with cwe_get_weakness/cwe_get_view when the agent already has an ID, so the when-not-to-use case is left implicit.

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