holded_write

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

Annotations already declare destructive=true, idempotent=false and openWorld=true; the description adds context they don't carry — that user authorization is required, that writes must not be retried automatically, and that uploads are capped at 10 MiB decoded. The response shape is also sketched. It doesn't say what an error or partial failure looks like, which matters for a destructive non-idempotent tool.

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 no padding; the operation type and the schema-inspection instruction are front-loaded. The oddly indented multi-line formatting in the middle costs a little readability but no content is wasted.

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?

Output schema exists, so skipping return-value detail is fine. For a destructive, non-idempotent, open-world generic write dispatcher, however, the description never explains how to obtain a valid operation_id, what happens when a write fails midway, or what "user authorization" concretely requires — the biggest gaps for this complexity level.

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 0%, so the description carries the full burden and it only discharges part of it: the files array is spelled out field-by-field with the size cap, which is genuinely valuable. The four other parameters (operation_id, body, query, path_params) get nothing beyond their names, and operation_id is the required one.

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 class (POST/PUT/PATCH/DELETE) and resource (a catalog operation identified by operation_id), and the read/write split against holded_read is implicit in the name plus the HTTP verb list. It never names a sibling tool or describes which Holded domain the operation targets, so the agent knows the shape of the action but not the surface area.

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?

"Inspect the schema first" and "never automatically retry failed writes" give real operational guidance about how to invoke it, and one exclusion is stated. But there is no guidance on where operation_id comes from (holded_search_operations / holded_get_operation) and no routing advice to the read counterpart, leaving the discovery workflow to inference.

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