declarations_agent_result

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

Annotations declare readOnlyHint=false and destructiveHint=false but say nothing about state transitions; the description fills exactly that gap by disclosing that the server parses the payload, extracts an upload ID, flips status to PROCESSING and starts status polling. That is real side-effect disclosure beyond the structured fields. It omits error/retry behavior, which matters given idempotentHint=false.

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 sentences and zero filler: the action first, then the chain of server effects. Nothing repeats the tool name or the schema, and the pipeline narrative is front-loaded where an agent will read it.

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 state-mutating tool with no output schema, the description covers the essential invisible work (parse, extract ID, set PROCESSING, dispatch polling). What is missing is what the caller receives back and what happens on a malformed body, given the tool is non-idempotent.

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 100%, so all five parameters (id, statusCode, body, headers, companyId) are already documented in the schema. The description adds no parameter-level meaning, such as which fields are actually parsed for the upload ID. Baseline 3 is correct when the schema does the work.

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?

Specific verb ('Submit') plus a clearly scoped resource ('the ANAF response received via the local agent') and the server-side consequences. An agent can tell this is the callback half of an agent round-trip, distinct from declarations_file_via_agent (outbound) and declarations_get (read). It stops short of naming the siblings it differs from.

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?

The phrase 'received via the local agent' implies this is called after the local agent has the ANAF response, so usage is inferable. But there is no explicit trigger condition, no statement of what to do if the agent call fails, and no pointer to the related siblings (spv_sync_agent_result, spv_request_agent_result) that share this pattern.

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