log_errors

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context: the exact error block patterns it recognizes, that repeats are grouped, and that mods are matched via cached chunk preview plus which mods were active at that time.

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?

Two dense sentences, front-loaded with the core action before edge details. The parenthetical pattern examples are worth their space, though the second sentence is somewhat compressed.

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 non-trivial parsing tool with four undocumented parameters and no output schema, the description should explain the return shape (what a grouped error entry contains) and clarify `limit`/`which`. It describes the analysis behavior well but leaves these gaps for an agent to guess.

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 0%, so the description carries full burden. It explains `tail` (last N log lines) and gives a concrete format for `since`, which is genuinely useful, but leaves `limit` and especially `which` (the log file selector in a tool hard-coding gen/log.txt) 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 (Parse) and resource (Lua errors in gen/log.txt), plus the two transformations applied (group repeats, map to cached mods). This clearly distinguishes it from siblings like read_log and log_tail, which merely surface raw log content.

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?

The description implies the tool is for diagnosing Lua errors and correlating them to mods, but never states when to prefer it over read_log, log_tail, or the watch_log_* family. No explicit when/when-not or alternative routing is given.

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