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

Goes well beyond the destructiveHint/idempotentHint annotations: tenant-wide blast radius (any member can delete regardless of creator), the exact failure mode and error payload for defaults, and the post-delete referential behavior (expenses keep category_id and render as Uncategorized, nothing reassigned or blocked). That is precisely the information an agent needs before an irreversible action.

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?

One front-loaded sentence that starts with the action, then layers scope, failure mode, and side effects in priority order. No filler, no restatement of the tool name.

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 destructive tool with no output schema, it covers permissions, error behavior, and consequences for referencing expenses. The remaining hole is the unexplained extra parameters.

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 only 14% (only 'id' is documented), yet the description says nothing about parameters. Worse, the schema exposes six extra properties (icon, name, slug, color, is_default, sort_order) on a delete operation with no explanation of whether they are ignored or used for matching — a real ambiguity the description should resolve.

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?

States a specific verb and resource ('Deletes a custom category') and immediately narrows scope: custom-only, tenant-shared, seeded defaults excluded. An agent can distinguish this from expense_category_update/expense_category_list without opening any schema.

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?

Gives a clear when-not-to-use rule (the 9 seeded defaults are undeletable and return CONFLICT with default_category: true), which prevents a whole class of failed calls. It does not name a sibling alternative for renaming/recoloring (e.g. expense_category_update), so routing is slightly incomplete.

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