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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely new behavioral facts: the no-quote mode returns changes in document order and truncates at the first 20. It also scopes coverage to documents, not files. It does not say what happens on a quote that matches multiple passages or nothing.

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 scope statement and the quote/no-quote branching are correctly front-loaded, and every clause carries information. The second half is a single very long run-on sentence whose clause list (AI, prompt, what they did themselves, where from, what AI read) is dense and slightly hard to parse in one pass.

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 shape need not be described, and the description still covers the important call-time facts: document-only scope, the truncation to 20 items, and the mode switch driven by quote. Missing is guidance on ambiguous or zero quote matches, which matters for a lookup tool keyed on free text.

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 a 3 baseline would apply, but the description adds meaning the schema does not: quote scopes the answer to that passage and its absence switches the whole response mode to per-line-run changes. The '§ address' phrasing reinforces the schema's note that a section address reads its whole document.

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 framing ('Why something on the project is the way it is, and who put it there') and then enumerates the specific facts returned: authorship, which AI, prompts, manual work, provenance, and sources read. That makes the resource and verb recoverable despite the cryptic tool name 'why'. It stops short of distinguishing itself from near siblings such as history, what_changed, or read.

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?

It gives a clear usage context and an explicit exclusion ('Documents only, not files'), and it explains the two modes: quote supplied → answer for that passage; no quote → change behind each run of lines in document order. What it omits is naming the alternatives (history, what_changed) that an agent should choose instead when it wants raw change data.

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