Delete compendium entries

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

The description goes well beyond the annotations. It discloses that only explicitly named entries are removed, that names are matched exactly and never as a part, that ambiguous names are reported rather than guessed, that dryRun changes nothing, and that unlockIfNeeded lifts a lock only for the one operation and sets it again. These are behavioral traits not visible in the annotations or schema.

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?

The description is compact and front-loaded. The first sentence states the core action and selection modes. The second sentence gives the critical safety instruction (dryRun first). Every sentence adds distinct information: no bulk deletion, exact matching, ambiguity handling, confirmLabel condition, and permission requirement. No filler or repetition.

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 tool with 6 parameters and no output schema, the description covers the essential context: what gets removed, how selection works, the safety workflow (dryRun), the edge case (all entries require confirmLabel), the permission requirement, and the lock behavior. An agent has enough to invoke this tool correctly and safely.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the relationship between ids and names (exact spelling, ambiguity handling), the purpose of dryRun ('reports exactly what would go'), and the condition for confirmLabel ('selection covers every entry'). It doesn't add much about unlockIfNeeded beyond the schema, but the overall added value justifies a 4.

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 verb ('Remove'), a specific resource ('named entries from a compendium'), and the two selection modes ('by id or by exact name'). It also distinguishes itself from a generic delete by explicitly noting there is 'deliberately no empty this pack', which separates it from sibling tools like delete-compendium and delete-document.

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 explicit usage guidance: 'Always run with dryRun first' and explains what dryRun reports. It also states when confirmLabel is required ('If the selection covers every entry') and what permission is needed ('compendium permission on create, change and delete'). This is clear when-to-use and how-to-use guidance.

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