export_graph

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

Annotations cover read-only/destructive/idempotent hints; description adds that the output is a self-contained offline HTML file and that the call returns the file path. This aligns with readOnlyHint=false and idempotentHint=true, though overwrite behavior is not detailed.

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?

Single, front-loaded sentence with no filler; the parenthetical mode breakdown is compact and informative.

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?

All parameters are schema-documented, annotations cover safety, and the description supplies the return value ('file path') and the artifact's purpose. No critical details are missing for a tool that writes a file.

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 already describes all 5 params at 100% coverage, but the description adds functional meaning: mode=symbol relates to blast radius, mode=module to imports/dependents. This helps select target semantics beyond the schema's terse enum.

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?

States a specific verb 'Write' and resource 'self-contained offline HTML view', and clarifies two modes: symbol blast radius versus module imports/dependents. This distinguishes it from siblings like find_usages or impact, which presumably return structured data rather than an HTML artifact.

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 clear usage context: produce a human-readable offline HTML report to open or attach to a PR. It does not explicitly name alternatives or when-not conditions, but the 'for a human' phrasing implies a choice over data-returning tools.

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