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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds a genuinely new behavioral fact: the input text is read and discarded, not stored, which is meaningful for an agent handling potentially sensitive log data.

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?

Three tight sentences: purpose first, then input format, then return shape and privacy note. Nothing is padded and each sentence carries distinct information.

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 the description need not enumerate return values, though it does summarize them. Input format, scope, and data-handling behavior are all covered; an agent has everything needed to call this correctly.

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 100% and there is only one parameter, so the baseline is 3. The description adds real guidance beyond the schema by specifying that the text must be the entire, unedited crash report or log, and naming the typical file locations.

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 and resource: find the mod responsible for a modded Minecraft crash, and scopes it to the loader families (Fabric, NeoForge, Forge). An agent immediately knows this is a crash-diagnosis tool, distinct from the sibling tools mod_lab_runs and mod_pair.

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?

Tells the caller exactly what to feed it — a full crash report (crash-reports/*.txt) or logs/latest.log — and specifies unedited text. It gives clear context for invocation but names no alternatives or exclusion conditions versus the sibling tools.

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