asana_find_duplicates

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

Beyond the readOnlyHint annotation, the description adds critical behavior: multi-homed tasks are NOT duplicates, and deleting one removes the task from every board. It also announces the return structure. This goes well beyond the annotations and prevents a common destructive mistake.

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 dense but efficiently engineered: the core purpose and the key non-intuitive warning (multi-homed vs duplicate) come first. It's a single structured run-on sentence with clear punctuation, packing in purpose, scope options, output contract, and a safety warning without any empty 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?

For a read-only, no-output-schema tool with 5 optional parameters, the description covers the dedup logic, the scan scopes, and the returned object shapes. It lacks details on pagination (max_pages) and completion filter, but those are present in the schema with descriptions. Nothing needed for correct invocation is missing.

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?

The schema already covers 80% of parameters. The description adds cross-board semantics for 'projects' and clarifies that 'project', 'section', and 'projects' are alternative scan scopes. It does not explain 'max_pages' or 'include_completed' beyond the schema, but those have descriptions and the description intentionally focuses on the selection logic.

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 exactly what the tool does: it finds TRUE duplicate tasks and distinguishes them from multi-homed (shared) tasks. It names the verb, the resource (tasks), and the specific dedup logic, which clearly differentiates it from sibling tools like asana_duplicate_task and asana_delete_task.

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?

It gives concrete scope guidance: scan one project/section or pass multiple projects for cross-board dedup. It also tells the agent to 'reason before you delete', implying the primary use case is pre-deletion analysis. However, it does not explicitly name alternative tools or state when NOT to use this tool, relying on implication rather than direct comparison.

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