Reads back a past report for an analysis ID, choosing the file with the later modification time across candidate directories to support session continuation.
過去レポートを読み戻す（候補ディレクトリ横断で最新更新のものを返す）。セッション継続用。
解析フォルダ配下と退避先の両方に同名レポートが残る場合（書き込み可否が途中で変化した等）、 古い方を返さないよう mtime が最新のファイルを採用する。
| Name | Required | Description | Default |
|---|---|---|---|
| analysis_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description is consistent with that while adding genuinely non-obvious behavior: it searches multiple candidate directories (analysis folder plus fallback) and resolves same-name collisions by newest mtime to avoid returning a stale copy. It omits what happens when no report exists (error vs empty) and what the returned report looks like.
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 core action and its scoping rule are front-loaded in the first sentence, with the mtime rationale following as supporting detail. Slightly verbose in the parenthetical explanation but no filler.
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?
No output schema exists, so the description should convey what a returned report contains and what happens on a miss; neither is covered. The directory-collision behavior is well explained, but the missing-parameter documentation and absent return/failure semantics leave real gaps.
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 0% for the single required parameter analysis_id, so the schema contributes nothing. The description never mentions analysis_id, its format, or how to obtain it, leaving the only input entirely undocumented.
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 specific verb+resource: reads back a past report and returns the most recently updated copy across candidate directories. It is distinguishable from write_report and list_reports by name and verb. It stops short of explicitly naming those siblings or clarifying the read-vs-list distinction.
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?
'セッション継続用' (for session continuation) implies the context of use but gives no explicit when-not condition or alternative routing. The duplicate-resolution note explains internal selection logic, not when an agent should call this versus list_reports or write_report.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.