Knowledge-loss risk

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. Beyond that, the description adds genuinely useful behavioral detail: the orphaned-file threshold (>50% inactive ownership), the three rollup shapes returned, and the notion that the analysis is scoped to tracked text files. It stops short of noting cost or performance implications of blaming up to max_files files.

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?

A tight single paragraph: the framing question is front-loaded, then method, then threshold definition, then return shape. The rhetorical opener costs little and earns its place by situating the tool. No filler or repetition.

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?

With a full output schema, annotations covering the safety profile, and 100% parameter coverage, the description only needs to carry conceptual framing — which it does, including the analysis methodology and the orphaned-file rule. The one meaningful gap is that bus_factor, the closest sibling, is never mentioned to help the agent disambiguate.

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 schema fully documents all five parameters and the baseline of 3 applies. The description reinforces the conceptual meaning of inactive ownership (which underpins inactive_after) and the >50% rule, but adds no syntax or semantics beyond what the schema already provides.

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 states a specific verb+resource with unusual precision: it blames tracked text files, compares line ownership against each author's last commit, and defines 'orphaned' files at >50% inactive ownership. That is enough for an agent to understand the analysis. It never names or contrasts with the nearest sibling, bus_factor, which measures a related-but-distinct concept, so sibling differentiation is absent.

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?

Usage is implied rather than stated: the lead question 'What breaks if someone leaves?' frames the scenario, and the methodology makes it clear this is a post-departure risk audit. There is no explicit when-to-use / when-not-to-use and no routing to alternatives such as bus_factor or blame_summary, which an agent must infer.

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