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

The word "Soft-delete" is genuinely valuable because it tells the agent the effect is recoverable rather than permanent, and "owned by the authenticated user" discloses the authorization boundary. However, the two "Safety" clauses largely restate the supplied annotations (openWorldHint=false, destructiveHint=true) rather than adding new detail such as cascade effects on activities referencing the category or how to undo the soft delete.

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?

Three short sentences with the action, scope, and selector front-loaded, and no filler or marketing language. The trailing "Safety" block is mildly redundant with the annotations, but it is compact enough not to obscure the primary sentence.

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 one-parameter delete tool with an output schema and full annotation coverage, the essentials are present, so the agent knows what it deletes and whose data it touches. What remains missing is the consequence detail that matters for a destructive operation: what happens to trips or activities referencing the category, and whether/when the soft delete can be reversed.

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 description coverage is 100% and there is a single required parameter documented as 'Tripsy resource id'. The description's "by id" and "owned by the authenticated user" only confirm what the schema implies, adding no format, naming, or lookup guidance (e.g. how to obtain the id). Baseline 3 applies.

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 names a specific verb and mode ("Soft-delete"), a specific resource ("custom activity category"), an ownership scope ("owned by the authenticated user"), and the key selector ("by id"). That is enough to distinguish it from the sibling categories_create, categories_update, categories_show, and categories_list without opening their schemas.

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?

Usage is only implied by the verb: an agent can infer 'call this when a category should go away', but nothing states when to prefer this over categories_update (e.g. renaming/archiving) or whether a soft-deleted category can be restored. No prerequisites or exclusions are given, so the agent must infer selection logic.

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