topology_affected

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

With no annotations provided, the description carries the full behavioral burden, and it succeeds: it discloses the heuristic nature of results, the deliberate recall bias (counting every test in a reached package), the cross-package import edge rule, language-dependent command formatting, and the behavior when topology is disabled. This is exemplary transparency for a complex tool.

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 long, but it is front-loaded with the core purpose and every subsequent sentence adds necessary operational detail (output shape, path handling, reachability rules, cap behavior). It could be tightened with bullet points, but it avoids fluff and each clause earns its place.

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?

Given the tool's complexity, the absence of an output schema, and the absence of annotations, the description is remarkably complete. It covers input expectations, output structure, per-language command behavior, recall bias, heuristics, max_results semantics, ordering guarantees, and failure mode when topology is disabled. An agent has enough information to invoke and interpret the result correctly.

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%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: files and symbols are "change roots," max_results bounds PACKAGES rather than test rows, and the changed package is always sorted first so a cap cannot drop it. This goes beyond what the schema descriptions already state.

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 a concrete use case: "After you change code, ask this which tests to run instead of running the whole suite." It names a specific resource (affected PACKAGES) and a specific output (packages with test counts, reasons, and individual test names), which clearly distinguishes it from siblings like topology_status, topology_search, and topology_impact.

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 gives clear context for when to use this tool — after code changes, to select tests rather than run everything. It implies the alternative (running the full suite) but does not explicitly name other topology or test-selection tools or state when not to use it, so it stops short of full exclusion guidance.

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