dedupe_mod

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

With no annotations present, the description carries the full load and does it well: it declares the tool destructive, enumerates exactly what is destroyed (jar plus its packwiz index entry), states that the jar is backed up first per server safety rules, and names the required confirm: true gate. That is the full risk profile an agent needs before a mutation.

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 covering scope, effects, and safety, followed by a short two-word destructive/confirm warning. The critical information (destructive, requires confirm) is front-loaded in the trailing fragment and nothing is redundant.

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 an unannotated destructive tool with no output schema, this covers prerequisites, side effects, reversibility (backup), and the confirmation gate. It leaves minor unknowns — behavior when the pair is not actually a duplicate, and whether the packwiz entry restoration accompanies the jar backup — but nothing that would cause a wrong invocation.

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%, so the description must compensate; it clarifies the two non-obvious parameters — `keep` is the source retained, with the other source's copy removed, and `confirm: true` is mandatory for destruction. `instance` and `slug` are only implied by context and get no explanation, leaving a modest gap at full 0% coverage.

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 precise verb and object — resolving a true cross-source duplicate — and defines that term in-line (a mod installed from both Modrinth and CurseForge). This clearly separates it from remove_mod (generic removal) and cross_check_mods (detection only).

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 phrase 'as reported by cross_check_mods' tells the agent when to reach for this tool and which upstream tool produces the qualifying condition, and 'true cross-source duplicate' implicitly excludes same-source duplicates. It does not explicitly say what to use instead if a mod is not a cross-source duplicate (presumably remove_mod), so it stops short of 5.

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