anon_get_physical_categories

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds genuinely non-obvious behavior: ascending 'order' sort, and that the first call lazily seeds six default categories when none exist. This seeding is the most important thing an agent should know and is not derivable from annotations or schema. It stops short of covering error/auth-failure behavior or return characteristics, hence not a 5.

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?

Purpose is front-loaded, followed by the two behavioral facts that matter (ordering, seeding); the parenthetical list of default categories is informative and compact. The raw endpoint line 'GET /api/projects/{id}/physical/categories' is largely redundant for MCP invocation and is the only wasted element.

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?

No output schema exists, and the description covers ordering and lazy-seeding well, but it never describes the shape of the returned categories (id/name/order) that a caller would likely need to feed into anon_delete_physical_categories_cat_id or the patch/reorder tools. For a 0-param read tool this is a minor but real gap.

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?

With zero parameters, the baseline is 4, and the description earns it by explaining why: the project is auto-resolved from the current API key, so no projectId is needed. That clarifies the implicit invocation context that the empty schema cannot express. It does not describe how the implicit project scope could be overridden, so it stays at 4 rather than 5.

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 opening sentence states a specific verb+resource: '列出实物分类' (list physical categories). The resource noun is precise enough to distinguish it from siblings such as anon_get_physical_items (items, not categories), anon_post_physical_categories (create), and anon_patch_physical_categories_reorder/patch/delete — an agent can route correctly 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?

'项目成员可用' tells the agent the access condition (project members), which is useful context. However, there is no explicit when-to-use vs. when-not-to-use guidance and no named alternative (e.g., 'use get_physical_items for individual items'); usage is only implied by the resource name.

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