audit_tree

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered structurally. The description adds the audit categories and confirms the output is a prioritized to-do list, but says nothing about how the `limit` caps findings, whether long trees are truncated, or reporting format.

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?

One dense sentence, front-loaded with the verb and resource, then the finding categories and the outcome. No filler, though the parenthetical example list is long enough to blunt the front-loading slightly.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. Still, a 4-parameter tool with an unexplained `limit` and `lang`, plus no routing guidance against the many sibling research tools, leaves gaps an agent would have to guess at.

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 only 50% — `lang` and `limit` carry no descriptions anywhere, and the description never explains them (e.g. does limit truncate the checklist?). The `file` and `codes` semantics are already fully documented in the schema, so the description adds essentially nothing for parameters despite the coverage gap.

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 concrete verb (audit) and resource (family tree / GEDCOM) and enumerates the exact classes of findings it produces (impossible facts, duplicates, gaps). No sibling tool performs auditing, so it is trivially distinguishable, and the 'to-do list for the next search' framing clarifies the output's purpose.

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 only implied: the 'to-do list for the next search' hint suggests running it before planning searches, but it never says when to prefer this over plan_research, find_sources, or where_are_records, nor any prerequisites. Adequate context, no explicit when/when-not guidance.

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