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

Annotations already declare readOnly, idempotent, non-destructive behavior. The description adds useful behavioral context beyond those flags: default revision resolution (head = session effective revision, base = previous indexed), the union blast radius across layers and cross-repo, and the prerequisite indexing step for uncommitted edits. It doesn't contradict annotations.

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 dense but efficient: three sentences cover purpose, output categories, sibling replacement, defaults, and the uncommitted workflow. The first sentence is a little long and packed with clauses, but every piece of information earns its place and the most important guidance appears early.

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 a read-only analytical tool with no output schema, the description provides the needed purpose, defaults, alternative routing, and a special-case workflow. It doesn't spell out the response structure, but the listed output categories (changed files, blast radius, endpoints, test suites, co-change reminders) give a reasonable expectation. Minor gap: how the results map to future reference or relate calls.

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 real value by explaining default base/head semantics and the 'call with no shas' pattern following an uncommitted-edit indexing step, which helps the agent decide when to omit parameters despite the schema already describing each parameter individually.

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 clearly states the tool computes the impact of a diff between two indexed revisions, listing specific output categories (changed files, symbols, blast radius, endpoints, test suites, co-change reminders). It also names the sibling it replaces (per-symbol relate blast_radius loops), making it distinguishable from related tools.

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 usage context: 'before merging' as the trigger, names the alternative it replaces (relate loops), explains default behavior for omitted shas, and gives a concrete workflow for uncommitted edits ('run ref (op:"index_working_tree"), then call with no shas'). This gives an agent clear when-and-how-to-use guidance.

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