Delete keys

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, but they do not convey the crucial default-preview behavior. The description supplies exactly that (preview unless dryRun:false or dialog confirmation), which is real value beyond structured fields. It omits recovery/undo and non-existent-key behavior.

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 tight sentences with the destructive-action caveat front-loaded immediately after the purpose. Every clause earns its place and nothing is padded.

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 destructive, four-parameter tool with no output schema, the description covers the safety mechanism an agent most needs to avoid accidental data loss. Missing only edge-case behavior (missing keys, reversibility), which is minor given the annotation set.

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 75% and the schema already documents dryRun ('Default true (preview). false deletes.') and locales, so the description's 'dryRun:false' and 'all or selected locales' largely restate structured fields rather than adding syntax or format detail. No meaning is added for keys or workspaceDir.

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 (remove) plus resource (keys) and scope (all or selected locales), which cleanly distinguishes it from siblings like i18n_rename_key and i18n_upsert_translations. It stops short of explicitly naming an alternative to route against, so not a 5.

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 operational guidance: the call previews by default, and deletion requires dryRun:false or confirming the dialog. It does not, however, say when to prefer this over rename_key or upsert_translations, leaving sibling routing unaddressed.

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