anon_post_physical_categories

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds value beyond that by disclosing the authorization model (materials:manage, project:manage equivalence, super-admin bypass) and the API-key-based project scoping, neither of which appears in the structured fields. It does not explain the return shape or duplicate handling, but the auth disclosure is substantive.

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?

Four short lines, front-loaded with purpose, then permission, then endpoint, then the projectId clarification. No filler, and the most decision-relevant facts come first. Slightly fragmented formatting but well within acceptable size.

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 non-idempotent mutation with no output schema and a nested body, the description covers purpose, auth, and scoping adequately but omits what success returns (e.g., the new category id) and any error/duplicate behavior. With no output schema to lean on, that is a noticeable gap rather than a critical one.

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 0% and the single parameter is a nested body object containing a required name, which the description never describes. It does add one genuinely useful semantic: that projectId must not (and need not) be passed because the project derives from the API key. That partially compensates, but the body.name field itself is left entirely to the schema.

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+resource ('新建实物分类' = create a physical category), which is instantly distinguishable from the sibling reads (get_physical_categories), patches (patch_physical_categories_cat_id), and deletes (delete_physical_categories_cat_id). It does not explicitly name those siblings, but the operation is unambiguous.

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?

Provides real selection context: the required materials:manage permission (with project:manage as an equivalent bypass and super-admin exemption) and the note that project is auto-resolved from the API key. However, it never states when to reach for this tool over patch/delete/reorder siblings, so guidance is implied rather than spelled out.

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