topology_explore

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

With no annotations, the description carries the full burden. It discloses return contents (centre node, neighbours, edges), bounded behaviour (depth/max_nodes/max_bytes), truncation reporting, approximation, and error cases. It does not explicitly state read-only safety, but the BFS/query framing implies it, so minor gap.

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?

Four dense, purposeful sentences: what it does, what it returns, truncation, caveat about approximation, and error conditions. No fluff, no repetition. The key point is front-loaded.

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?

For an 8-parameter tool with no output schema, the description covers purpose, return types, limits, truncation, error cases, and alternative tools. It doesn't detail the exact JSON structure of returned nodes/edges, but that level is often unnecessary as long as the schema defines parameters. Overall sufficient.

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%, so the baseline is 3. The description adds no parameter-specific meaning beyond what the schema already provides (e.g., it mentions limits but not formats or semantics of edge_kinds/include_source). No extra value beyond the schema.

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 'Bounded BFS neighbourhood around a named symbol in the topology index', a specific verb+resource+scope. It also distinguishes itself from LSP semantic tools ('use LSP semantic tools for authoritative') and from sibling topology tools by emphasizing the bounded neighbourhood and limits.

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?

Provides explicit guidance: 'use LSP semantic tools for authoritative reference and definition lookups' tells the agent when not to rely on this tool. Also states error conditions (topology disabled, symbol not in index) which imply when the tool is unusable and helps with fallback decisions.

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