Explain and recover from a failed tool call

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

Goes well beyond the annotations by enumerating what the recovery envelope contains (cause, evidence, confidence, retry safety, correctedInput, ranked fallback tools, script, next actions) and stating strong behavioral guarantees ('never invokes a fallback and never recommends repeating an identical failed mutation'). This adds real value on top of readOnlyHint/idempotentHint, though it restates read-only twice.

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?

Front-loads the key READ-ONLY constraint, but the body is dense and partly redundant: read-only is asserted three times (header, idempotency, Safety) and the Signature block duplicates the input schema. The metadata line (Phase/cost/idempotency/Requires/Produces) is boilerplate that could be trimmed.

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?

With no output schema, the description carries the burden of describing the return value, and it does so thoroughly by listing the envelope's contents. Combined with the safety guarantees and fallback behavior, it is largely complete for a complex five-parameter tool, with only minor overlap against the annotations.

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%, so the schema already documents all five parameters. The description's inline Signature restates those same fields and their optionality without adding syntax, format, or constraint detail beyond the schema, so the baseline 3 is appropriate.

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: 'Deterministically classify a failed MCP/Roblox tool call' from its error/result/input/context. This is unmistakably distinct from every sibling (tool-schema, tool-plan, agent-context, etc.), so an agent can route to it without opening the schema.

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?

Explicitly says 'Use this after any failed or blocked call,' giving a clear triggering condition. It also points to a concrete alternative ('inspect tool-schema for exact fields, defaults, constraints') for the schema-lookup case, though it does not enumerate when-not-to-use scenarios beyond that.

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