manage-category

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

The description discloses behavioral details beyond annotations: delete does not untag messages, and 'set' is deprecated. This adds transparency not available from the annotations alone, and 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?

The description is a single coherent paragraph that covers all actions without redundancy. It front-loads the purpose and efficiently organizes details for each action. Minor improvement could be breaking into sections, but it remains readable and concise.

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 multi-action tool with no output schema, the description covers what each action returns (e.g., list returns id/displayName/color), required parameters per action, and the deprecated parameter. It is complete and leaves no major gaps.

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 has full coverage of parameters (100%), so baseline is 3. The description adds value by explaining color presets (e.g., preset0=Red), clarifying the default action, and noting the alias 'set' is deprecated. This extra context warrants 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 clearly states it manages the 'master category list' and lists specific actions (list, create, update, delete). It distinguishes itself from sibling tool 'apply-category' by noting the latter is for tagging/untagging messages.

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 provides explicit guidance on when to use each action, mentions that 'set' is a deprecated alias for 'update', and directs users to 'apply-category' for tagging/untagging. It also explains the effect of delete not removing labels from existing messages.

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