graph_node

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

Annotations supply only readOnlyHint, so the description carries most of the burden and delivers: resolution is deterministic and ordered (id, then label), the tool refuses unresolvable input rather than approximating, and results are guaranteed to concern the named node. It adds no permission or rate-limit context, but the determinism/failure behavior is genuinely valuable beyond the annotation.

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?

Two dense sentences, front-loaded with the capability and then the resolution guarantee. No filler, though the second clause is emphatic enough to verge on rhetorical redundancy.

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?

There is no output schema, so the description correctly sketches the return shape: declaration location, inbound edges, outbound edges, and a connectivity measure. Combined with a read-only annotation and a fully documented 4-parameter schema, an agent has enough to call it correctly, though the connectivity metric is not quantified.

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% and the direction/relation/depth parameters are already well documented in the schema, including the in/out meaning. The description restates those semantics in prose ('what reaches it, what it reaches') without adding syntax, defaults, or edge-case behavior. Baseline 3 for a schema that does the heavy lifting.

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 names a concrete verb+resource: retrieve one symbol in full, covering its declaration site, incoming and outgoing edges, and connectivity. It implicitly separates itself from fuzzy-search siblings by stressing exact resolution and refusal of free text, though it never names an alternative tool explicitly.

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 gives a clear applicability condition — you must supply an exact node id or label — and a clear when-not: free text is never scored, so this is the wrong tool for fuzzy lookups. The only gap is that it doesn't name the sibling to use instead for text search.

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