catalog_write

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

Annotations already declare the safety profile (not read-only, not destructive, idempotent, open-world). The description adds one useful behavioral fact beyond them: there is no delete action and deletions live in delete_resource. However, it doesn't clarify how create vs update is disambiguated or what action_name controls, so it only modestly enriches the annotation picture.

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 sentences, front-loaded with the core purpose, followed by usage context and the deletion exclusion. No wasted prose, though the field enumeration is somewhat list-like rather than informative.

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?

An output schema exists so return values needn't be explained, and annotations cover the safety profile. But for a 26-parameter tool with 0% parameter coverage, the description leaves significant gaps around what catalog_type values exist and how action_name selects the operation, making it only minimally complete given the complexity.

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 26 parameters at 0% schema description coverage, the description carries the full documentation burden but only gestures at broad field categories. It never explains the two required parameters (catalog_type, action_name), which are the most critical for invocation, nor the integer IDs (parent_id, manager_id, depreciation_id, etc.). This leaves most parameter semantics undocumented in both schema and description.

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 gives a specific verb pair (create/update) and resource (Snipe-IT catalog records) and enumerates the field domains covered (model, status, hierarchy, contact, depreciation, type). It also distinguishes itself from delete_resource, so an agent can route writes vs deletes correctly. It stops short of naming the search sibling, but the scope is clear.

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?

"Use for normal requested configuration writes" tells the agent the operational context, and the explicit routing of all deletions to delete_resource acts as a strong when-not-to-use exclusion. It lacks guidance on how it relates to catalog_search or other write siblings, so it is not fully exhaustive.

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