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

Annotations already flag destructiveHint=true, and the description adds substantial context beyond them: atomicity of the batch, the 200 cap, per-id not-found behavior, cross-project blast radius on shared memories, and the repository-import caveat that deleted entries can reappear. This is exactly the extra behavioral detail annotations cannot convey.

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-loaded with the core action and scope before the caveats, and each sentence carries information. It is on the long side, and the trailing instruction about formatting names/locales in replies is useful but slightly tangential to tool selection.

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, cross-project-affecting tool, the description covers scope, atomicity, failure behavior, side effects, and the interaction with repository imports. With an output schema present it need not explain return shape, yet it still tells the agent the result lists affected projects.

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%: the schema already documents 'project' (UUID or slug) and 'entryIds' (1–200, from search_translation_memory). The description restates the id source and the limit but adds no syntax or format meaning beyond the schema, so the baseline 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?

States a specific verb and resource ('Delete ... entries ... from the translation memory attached to a project') with scope ('up to 200 entries, by id') and explicitly differentiates from the sibling that produces the ids ('from search_translation_memory'). An agent can distinguish it from delete_glossary_entry and other delete siblings without opening a 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 an explicit purpose ('remove faulty translations so future jobs stop reusing them'), the source of valid ids, and a concrete when-not/edge case (ids matching nothing are reported as not found and nothing is deleted). It also warns that the operation affects every project sharing the memory, which directly shapes whether/when to call it.

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