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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses that the call mutates underlying phrase rows into a shared state and that edits thereafter propagate to every attached project — an enduring side effect. This adds specificity about what changes and carries ongoing consequences, and it is consistent with destructiveHint=true, so there is no contradiction.

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 sentences with no filler: the first states the core action and scope, the second delivers the critical behavioral consequence. Nothing is repeated from the schema or annotations.

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 3-parameter mutation tool with full annotation coverage and an output schema, the description covers the core call scenario and its enduring side effect. The main gap is the unhandled edge case of a target project that already contains the same key, which is a plausible call given siblings like add_phrase and update_phrase exist.

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%: project is documented as the source id/name containing the key, key as the exact key across locales, and targetProjects as the attachments. The description's wording mirrors these definitions (source project, target projects, every locale translation) without adding new parameter-level detail, so the coverage baseline of 3 applies.

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?

The description states a specific action (Attach) on a concrete resource (every locale translation for one key in a source project) with a clear target (one or more target projects). The shared-row consequence in the second sentence distinguishes this from copy behavior and from siblings like add_phrase or update_phrase, which create or modify phrases rather than link them across projects.

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 description gives clear context for when to use the tool: attach a key's translations to target projects and keep them in sync, since future edits propagate to all attached projects. It does not name alternatives explicitly or state exclusion conditions (e.g., when a target project already contains the key), which keeps it just short of a 5.

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