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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: it clarifies that a missing rule changes nothing (reinforcing idempotency), that existing audio is preserved, and what the response reports. It does not spell out auth requirements, though the operation's blast radius is well characterized.

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 short sentences, each earning its place: purpose, effect/return behavior, and the exclusion. Purpose is front-loaded with 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?

Covers purpose, effect, idempotency behavior, and an explicit exclusion, which is complete for a simple two-parameter mutation. Mentioning the return value is somewhat redundant given an output schema exists, but it is harmless rather than misleading.

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%, with both projectId and word fully documented, so the schema carries the parameter burden. The description adds no syntax or format detail beyond what the schema provides, making the baseline 3 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+resource ('drop a pronunciation rule') and the resulting effect ('word is spoken the default way again'), which cleanly distinguishes it from the sibling set_pronunciation_rule. An agent can identify the operation 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?

Gives clear when-to-use context ('when someone wants to drop a pronunciation rule') and an explicit exclusion ('Not for changing a rule's phonemes'). It stops short of naming set_pronunciation_rule as the alternative, leaving the agent to infer the sibling route.

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