erpnext_input_append

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

The description adds genuine behavioral constraints beyond the annotations: the 256 KiB size limit and rejection of out-of-order or excess bytes are not present in the annotation flags. This tells the agent what inputs will fail. It does not explain why destructiveHint=true is set for an append operation, but no annotation contradiction exists.

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?

Two short sentences with no filler. The primary action is front-loaded, and the size limit plus rejection behavior both earn their place as operation-critical constraints. Nothing extraneous is present.

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?

The tool is one step in a stateful protocol, yet the description does not state that input_append requires an active session started by input_begin and must be completed by input_finalize. With 0% schema coverage and no mention of the workflow, offset semantics, or artifact_id meaning, an agent lacks enough context to call it correctly despite the output schema existing.

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 must compensate. It partially does: 'up to 256 KiB' bounds data_base64, and 'out-of-order ... rejected' explains that offset must follow sequence order. However, it leaves artifact_id's referent and whether offset is a byte position or chunk index unstated, which are critical for correct invocation.

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 states a specific verb and resource ('Append one local input chunk') with a size cap, which clearly identifies the operation. It is distinguishable from siblings like erpnext_input_begin and erpnext_input_finalize by the 'append' verb. The term 'local input' is somewhat vague without protocol context, but the core action 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?

Usage context is implied rather than explicit: 'append' suggests it fits between erpnext_input_begin and erpnext_input_finalize, and the sibling list reinforces that. However, the description never states the expected call sequence, prerequisites (an begun input session), or when to choose this over alternatives. The rejection of out-of-order chunks hints at protocol ordering but does not spell it out.

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