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

Beyond annotations (readOnlyHint false, destructiveHint false), the description adds useful behavioral details: it costs $0.001 per call and nothing if it fails, options adds options, rename renames them on every line, and archive stops new use. It does not explain permissions or idempotency (though idempotentHint is false), but the cost and action semantics go well beyond the annotation set.

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 contains valuable information but is structured as a dense conceptual explanation rather than front-loading the tool's action. The opening sentence defines a tracking category instead of stating 'Creates or updates a tracking category', so the agent must read several clauses before understanding the operation.

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 mutation tool with six parameters, no output schema, and low schema coverage, the description provides good context about effects and cost but omits when-to-use guidance, the role of new_name versus rename, and any permission or reversal details. It is adequate but leaves gaps an agent must resolve by inference.

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 only 17% (only archived is described in the schema), so the description must compensate. It explains that matching is by name, that options adds options, that rename renames them on every line, and that archive stops new use. It does not clarify the distinction between rename and new_name, leaving one parameter ambiguous, but it meaningfully documents most of the six parameters.

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 explains what a tracking category is ('like Xero's: a department, a region or a project line') and mentions actions ('options adds options, rename renames them', 'archive stops new use'), but never states a clear verb like 'Create or update' for the tool itself. The core action is buried in concept explanation, so an agent must infer that this is a save/mutation tool from the name alone.

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?

There is no explicit guidance on when to use this tool versus siblings like books_list_tracking or books_report. The description provides context ('Up to two at a time', 'Any line can then carry one option') but does not say when to choose this save operation or what prerequisites exist.

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