Scan board for cleanup

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'read-only deep-clean scan' and 'Never deletes'. It provides detailed behavioral context about what scans are performed (duplicates, staleness, missing labels, SLA breaches) beyond the annotations.

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 packed with information in two sentences, front-loaded with the core purpose. It could be slightly more concise but no unnecessary words. Every sentence adds value.

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?

Given no output schema, the description hints at the return value ('Returns a suggested removal set to feed prune_board') and explains all scanning categories. For a tool with 3 parameters and moderate complexity, it is complete and provides sufficient context for correct invocation.

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?

Input schema describes 'staleDays' and 'similarity' with defaults and descriptions; 'project' is required but not described in schema. The description adds value by mentioning the 'slaThresholds config key' for overriding thresholds, which is not a parameter but related configuration. Schema coverage is 67%, and the description partially compensates.

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 clearly states it's a 'read-only deep-clean scan' that finds duplicate tickets, stale tickets, missing labels, and SLA breaches. It distinguishes itself from the sibling tool 'prune_board' which actually deletes, making its purpose specific.

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 indicates it's a 'good fit for a recurring Cowork scheduled task' and explicitly states 'Never deletes', implying when to use it. It doesn't explicitly list when not to use it but the context makes it clear. Sibling tools like 'prune_board' are implied as alternatives for deletion.

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