related_symbols

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

No annotations are provided, so the description carries the burden, and it delivers: it discloses the algorithm (personalized PageRank), the undirected treatment of the call graph, and the non-obvious behavior of surfacing siblings/helpers rather than direct edges. It also clarifies that no embeddings are required, which is a meaningful operational trait. It stops short of explicit statements about read-only-ness or side effects, though the reading context strongly implies a safe query.

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 compact: a one-line use-case question, a two-sentence explanation of the algorithm and its value, and a one-sentence positioning against semantic search. It front-loads the user intent and each sentence earns its place. No redundant restatement of schema or annotations.

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?

The tool has moderate algorithmic complexity, and the description covers purpose, algorithm, outputs' conceptual nature, and how it differs from structural and semantic alternatives. An output schema exists, so not detailing the return payload is fine. The only minor gaps (exact sibling names, explicit exclusions) are small and already addressed in other dimensions.

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 covers both parameters with descriptions ('Anchor symbol (name, qualname or id)', 'Max results'), so the baseline for this dimension is 3. The description reinforces that symbol is the seed of the PageRank but adds no syntax, defaults, or format details beyond the schema. This is acceptable given high coverage.

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 defines a concrete operation: it runs personalized PageRank seeded on an anchor symbol over the call graph, computed undirected, to surface related symbols. It immediately distinguishes itself from sibling tools like who_calls/what_it_calls by stating it goes beyond a plain caller/callee list. The 'structural analogue of semantic search' framing makes the resource and intent unmistakable.

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 frames when to use it: when deciding 'what else should I read before touching this,' and contrasts it with a plain caller/callee list for discovering indirect collaborators. It indicates this tool is the structural alternative to semantic search and does not need embeddings, which guides tool selection. It does not explicitly name sibling tools or state a hard when-not-to-use, 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.